speech to text web api

DEV Community

Posted on Jan 2

Building a Real-time Speech-to-text Web App with Web Speech API

Happy New Year, everyone! In this short tutorial, we will build a simple yet useful real-time speech-to-text web app using the Web Speech API. Feature-wise, it will be straightforward: click a button to start recording, and your speech will be converted to text, displayed in real-time on the screen. We'll also play with voice commands; saying "stop recording" will halt the recording. Sounds fun? Okay, let's get into it. 😊

Web Speech API Overview

The Web Speech API is a browser technology that enables developers to integrate speech recognition and synthesis capabilities into web applications. It opens up possibilities for creating hands-free and voice-controlled features, enhancing accessibility and user experience.

Some use cases for the Web Speech API include voice commands, voice-driven interfaces, transcription services, and more.

Let's Get Started

Now, let's dive into building our real-time speech-to-text web app. I'm going to use vite.js to initiate the project, but feel free to use any build tool of your choice or none at all for this mini demo project.

• Create a new vite project:
• Choose "Vanilla" on the next screen and "JavaScript" on the following one. Use arrow keys on your keyboard to navigate up and down.

HTML Structure

CSS Styling

JavaScript Implementation

This simple web app utilizes the Web Speech API to convert spoken words into text in real-time. Users can start and stop recording with the provided buttons. Customize the design and functionalities further based on your project requirements.

Final demo: https://stt.nixx.dev

Feel free to explore the complete code on the GitHub repository .

Now, you have a basic understanding of how to create a real-time speech-to-text web app using the Web Speech API. Experiment with additional features and enhancements to make it even more versatile and user-friendly. 😊 🙏

Top comments (0)

Templates let you quickly answer FAQs or store snippets for re-use.

Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink .

Hide child comments as well

For further actions, you may consider blocking this person and/or reporting abuse

Husky and lint-staged: Keeping Code Consistent

Joy Lee - Jul 11

Unlocking the Power of ReactJS: Top Features Every Product Manager Should Know

Cache Merrill - Jun 27

Stop console.log. There are better ways.

OpenSource - Jul 10

5 Essential Flags to Enable on Your TypeScript Code

Gerald Hamilton Wicks - Jul 10

We're a place where coders share, stay up-to-date and grow their careers.

Web Speech API Demonstration

Click on the microphone icon and begin speaking for as long as you like.

No speech was detected. You may need to adjust your microphone settings .

No microphone was found. Ensure that a microphone is installed and that microphone settings are configured correctly.

Click the "Allow" button above to enable your microphone.

Permission to use microphone was denied.

Permission to use microphone is blocked. To change, go to chrome://settings/contentExceptions#media-stream

Web Speech API is not supported by this browser. Upgrade to Chrome version 25 or later.

Press Control-C to copy text.

(Command-C on Mac.)

Text sent to default email application.

(See chrome://settings/handlers to change.)

• Español – América Latina
• Português – Brasil
• Tiếng Việt
• Chrome for Developers

Web apps that talk - Introduction to the Speech Synthesis API

The Web Speech API adds voice recognition (speech to text) and speech synthesis (text to speech) to JavaScript. The post briefly covers the latter, as the API recently landed in Chrome 33 (mobile and desktop). If you're interested in speech recognition, Glen Shires had a great writeup a while back on the voice recognition feature, " Voice Driven Web Apps: Introduction to the Web Speech API ".

The most basic use of the synthesis API is to pass the speechSynthesis.speak() and utterance:

However, you can also alter parameters to effect the volume, speech rate, pitch, voice, and language:

Setting a voice

The API also allows you to get a list of voice the engine supports:

Then set a different voice, by setting .voice on the utterance object:

In my Google I/O 2013 talk, " More Awesome Web: features you've always wanted " ( www.moreawesomeweb.com ), I showed a Google Now/Siri-like demo of using the Web Speech API's SpeechRecognition service with the Google Translate API to auto-translate microphone input into another language:

DEMO: http://www.moreawesomeweb.com/demos/speech_translate.html

Unfortunately, it used an undocumented (and unofficial API) to perform the speech synthesis. Well now we have the full Web Speech API to speak back the translation! I've updated the demo to use the synthesis API.

Browser Support

Chrome 33 has full support for the Web Speech API, while Safari for iOS7 has partial support.

Feature detection

Since browsers may support each portion of the Web Speech API separately (e.g. the case with Chromium), you may want to feature detect each feature separately:

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License , and code samples are licensed under the Apache 2.0 License . For details, see the Google Developers Site Policies . Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2014-01-13 UTC.

• Português – Brasil

Using the Speech-to-Text API with Node.js

1. overview.

Google Cloud Speech-to-Text API enables developers to convert audio to text in 120 languages and variants, by applying powerful neural network models in an easy to use API.

In this codelab, you will focus on using the Speech-to-Text API with Node.js. You will learn how to send an audio file in English and other languages to the Cloud Speech-to-Text API for transcription.

What you'll learn

• How to enable the Speech-to-Text API
• How to Authenticate API requests
• How to install the Google Cloud client library for Node.js
• How to transcribe audio files in English
• How to transcribe audio files with word timestamps
• How to transcribe audio files in different languages

What you'll need

• A Google Cloud Platform Project
• A Browser, such Chrome or Firefox
• Familiarity using Javascript/Node.js

How will you use this tutorial?

How would you rate your experience with node.js, how would you rate your experience with using google cloud platform services, 2. setup and requirements, self-paced environment setup.

• Sign in to Cloud Console and create a new project or reuse an existing one. (If you don't already have a Gmail or G Suite account, you must create one .)

Remember the project ID, a unique name across all Google Cloud projects (the name above has already been taken and will not work for you, sorry!). It will be referred to later in this codelab as PROJECT_ID .

• Next, you'll need to enable billing in Cloud Console in order to use Google Cloud resources.

Running through this codelab shouldn't cost much, if anything at all. Be sure to to follow any instructions in the "Cleaning up" section which advises you how to shut down resources so you don't incur billing beyond this tutorial. New users of Google Cloud are eligible for the $300USD Free Trial program.

Start Cloud Shell

While Google Cloud can be operated remotely from your laptop, in this codelab you will be using Google Cloud Shell , a command line environment running in the Cloud.

Activate Cloud Shell

If you've never started Cloud Shell before, you'll be presented with an intermediate screen (below the fold) describing what it is. If that's the case, click Continue (and you won't ever see it again). Here's what that one-time screen looks like:

It should only take a few moments to provision and connect to Cloud Shell.

This virtual machine is loaded with all the development tools you'll need. It offers a persistent 5GB home directory and runs in Google Cloud, greatly enhancing network performance and authentication. Much, if not all, of your work in this codelab can be done with simply a browser or your Chromebook.

Once connected to Cloud Shell, you should see that you are already authenticated and that the project is already set to your project ID.

• Run the following command in Cloud Shell to confirm that you are authenticated:

Command output

If it is not, you can set it with this command:

3. Enable the Speech-to-Text API

Before you can begin using the Speech-to-Text API, you must enable the API. You can enable the API by using the following command in the Cloud Shell:

4. Authenticate API requests

In order to make requests to the Speech-to-Text API, you need to use a Service Account . A Service Account belongs to your project and it is used by the Google Client Node.js library to make Speech-to-Text API requests. Like any other user account, a service account is represented by an email address. In this section, you will use the Cloud SDK to create a service account and then create credentials you will need to authenticate as the service account.

First, set an environment variable with your PROJECT_ID which you will use throughout this codelab, if you are using Cloud Shell this will be set for you:

Next, create a new service account to access the Speech-to-Text API by using:

Next, create credentials that your Node.js code will use to login as your new service account. Create these credentials and save it as a JSON file ~/key.json by using the following command:

Finally, set the GOOGLE_APPLICATION_CREDENTIALS environment variable, which is used by the Speech-to-Text API Node.js library, covered in the next step, to find your credentials. The environment variable should be set to the full path of the credentials JSON file you created, by using:

You can read more about authenticating the Speech-to-Text API .

5. Install the Google Cloud Speech-to-Text API client library for Node.js

First, create a project that you will use to run this Speech-to-Text API lab, initialize a new Node.js package in a folder of your choice:

NPM asks several questions about the project configuration, such as name and version. For each question, press ENTER to accept the default values. The default entry point is a file named index.js .

Next, install the Google Cloud Speech library to the project:

For more instructions on how to set up a Node.js development for Google Cloud please see the Setup Guide .

Now, you're ready to use Speech-to-Text API!

6. Transcribe Audio Files

In this section, you will transcribe a pre-recorded audio file in English. The audio file is available on Google Cloud Storage.

Navigate to the index.js file inside the and replace the code with the following:

Take a minute or two to study the code and see it is used to transcribe an audio file*.*

The Encoding parameter tells the API which type of audio encoding you're using for the audio file. Flac is the encoding type for .raw files (see the doc for encoding type for more details).

In the RecognitionAudio object, you can pass the API either the uri of our audio file in Cloud Storage or the local file path for the audio file. Here, we're using a Cloud Storage uri.

Run the program:

You should see the following output:

7. Transcribe with word timestamps

Speech-to-Text can detect time offset (timestamp) for the transcribed audio. Time offsets show the beginning and end of each spoken word in the supplied audio. A time offset value represents the amount of time that has elapsed from the beginning of the audio, in increments of 100ms.

Take a minute or two to study the code and see it is used to transcribe an audio file with word timestamps*.* The EnableWordTimeOffsets parameter tells the API to enable time offsets (see the doc for more details).

Run your program again:

8. Transcribe different languages

Speech-to-Text API supports transcription in over 100 languages! You can find a list of supported languages here .

In this section, you will transcribe a pre-recorded audio file in French. The audio file is available on Google Cloud Storage.

Run your program again and you should see the following output:

This is a sentence from a popular French children's tale .

For the full list of supported languages and language codes, see the documentation here .

9. Congratulations!

You learned how to use the Speech-to-Text API using Node.js to perform different kinds of transcription on audio files!

To avoid incurring charges to your Google Cloud Platform account for the resources used in this quickstart:

• Go to the Cloud Platform Console .
• Select the project you want to shut down, then click ‘Delete' at the top: this schedules the project for deletion.
• Google Cloud Speech-to-Text API: https://cloud.google.com/speech-to-text/docs
• Node.js on Google Cloud Platform: https://cloud.google.com/nodejs/
• Google Cloud Node.js client: https://googlecloudplatform.github.io/google-cloud-node/

This work is licensed under a Creative Commons Attribution 2.0 Generic License.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License , and code samples are licensed under the Apache 2.0 License . For details, see the Google Developers Site Policies . Java is a registered trademark of Oracle and/or its affiliates.

• Skip to main content
• Skip to search
• Skip to select language
• Sign up for free

SpeechRecognition

The SpeechRecognition interface of the Web Speech API is the controller interface for the recognition service; this also handles the SpeechRecognitionEvent sent from the recognition service.

Note: On some browsers, like Chrome, using Speech Recognition on a web page involves a server-based recognition engine. Your audio is sent to a web service for recognition processing, so it won't work offline.

Constructor

Creates a new SpeechRecognition object.

Instance properties

SpeechRecognition also inherits properties from its parent interface, EventTarget .

Returns and sets a collection of SpeechGrammar objects that represent the grammars that will be understood by the current SpeechRecognition .

Returns and sets the language of the current SpeechRecognition . If not specified, this defaults to the HTML lang attribute value, or the user agent's language setting if that isn't set either.

Controls whether continuous results are returned for each recognition, or only a single result. Defaults to single ( false .)

Controls whether interim results should be returned ( true ) or not ( false .) Interim results are results that are not yet final (e.g. the SpeechRecognitionResult.isFinal property is false .)

Sets the maximum number of SpeechRecognitionAlternative s provided per result. The default value is 1.

Instance methods

SpeechRecognition also inherits methods from its parent interface, EventTarget .

Stops the speech recognition service from listening to incoming audio, and doesn't attempt to return a SpeechRecognitionResult .

Starts the speech recognition service listening to incoming audio with intent to recognize grammars associated with the current SpeechRecognition .

Stops the speech recognition service from listening to incoming audio, and attempts to return a SpeechRecognitionResult using the audio captured so far.

Listen to these events using addEventListener() or by assigning an event listener to the oneventname property of this interface.

Fired when the user agent has started to capture audio. Also available via the onaudiostart property.

Fired when the user agent has finished capturing audio. Also available via the onaudioend property.

Fired when the speech recognition service has disconnected. Also available via the onend property.

Fired when a speech recognition error occurs. Also available via the onerror property.

Fired when the speech recognition service returns a final result with no significant recognition. This may involve some degree of recognition, which doesn't meet or exceed the confidence threshold. Also available via the onnomatch property.

Fired when the speech recognition service returns a result — a word or phrase has been positively recognized and this has been communicated back to the app. Also available via the onresult property.

Fired when any sound — recognizable speech or not — has been detected. Also available via the onsoundstart property.

Fired when any sound — recognizable speech or not — has stopped being detected. Also available via the onsoundend property.

Fired when sound that is recognized by the speech recognition service as speech has been detected. Also available via the onspeechstart property.

Fired when speech recognized by the speech recognition service has stopped being detected. Also available via the onspeechend property.

Fired when the speech recognition service has begun listening to incoming audio with intent to recognize grammars associated with the current SpeechRecognition . Also available via the onstart property.

In our simple Speech color changer example, we create a new SpeechRecognition object instance using the SpeechRecognition() constructor, create a new SpeechGrammarList , and set it to be the grammar that will be recognized by the SpeechRecognition instance using the SpeechRecognition.grammars property.

After some other values have been defined, we then set it so that the recognition service starts when a click event occurs (see SpeechRecognition.start() .) When a result has been successfully recognized, the result event fires, we extract the color that was spoken from the event object, and then set the background color of the <html> element to that color.

Specifications

Browser compatibility

BCD tables only load in the browser with JavaScript enabled. Enable JavaScript to view data.

• Web Speech API

• About AssemblyAI

The top free Speech-to-Text APIs, AI Models, and Open Source Engines

This post compares the best free Speech-to-Text APIs and AI models on the market today, including APIs that have a free tier. We’ll also look at several free open-source Speech-to-Text engines and explore why you might choose an API vs. an open-source library, or vice versa.

Choosing the best Speech-to-Text API , AI model, or open-source engine to build with can be challenging. You need to compare accuracy, model design, features, support options, documentation, security, and more.

This post examines the best free Speech-to-Text APIs and AI models on the market today, including ones that have a free tier, to help you make an informed decision. We’ll also look at several free open-source Speech-to-Text engines and explore why you might choose an API or AI model vs. an open-source library, or vice versa.

Looking for a powerful speech-to-text API or AI model?

Learn why AssemblyAI is the leading Speech AI partner.

Free Speech-to-Text APIs and AI Models

APIs and AI models are more accurate, easier to integrate, and come with more out-of-the-box features than open-source options. However, large-scale use of APIs and AI models can come with a higher cost than open-source options.

If you’re looking to use an API or AI model for a small project or a trial run, many of today’s Speech-to-Text APIs and AI models have a free tier. This means that the API or model is free for anyone to use up to a certain volume per day, per month, or per year.

Let’s compare three of the most popular Speech-to-Text APIs and AI models with a free tier: AssemblyAI, Google, and AWS Transcribe.

AssemblyAI is an API platform that offers AI models that accurately transcribe and understand speech, and enable users to extract insights from voice data. AssemblyAI offers cutting-edge AI models such as Speaker Diarization , Topic Detection, Entity Detection , Automated Punctuation and Casing , Content Moderation , Sentiment Analysis , Text Summarization , and more. These AI models help users get more out of voice data, with continuous improvements being made to accuracy .

AssemblyAI also offers LeMUR , which enables users to leverage Large Language Models (LLMs) to pull valuable information from their voice data—including answering questions, generating summaries and action items, and more. 

The company offers up to 100 free transcription hours for audio files or video streams, with a concurrency limit of 5, before transitioning to an affordable paid tier.

Its high accuracy and diverse collection of AI models built by AI experts make AssemblyAI a sound option for developers looking for a free Speech-to-Text API. The API also supports virtually every audio and video file format out-of-the-box for easier transcription.

AssemblyAI has expanded the languages it supports to include English, Spanish, French, German, Japanese, Korean, and much more, with additional languages being released monthly. See the full list here .

AssemblyAI’s easy-to-use models also allow for quick set-up and transcription in any programming language. You can copy/paste code examples in your preferred language directly from the AssemblyAI Docs or use the AssemblyAI Python SDK or another one of its ready-to-use integrations .

• Free to test in the AI playground , plus 100 free hours of asynchronous transcription with an API sign-up
• Speech-to-Text – $0.37 per hour
• Real-time Transcription – $0.47 per hour
• Audio Intelligence – varies, $.01 to $.15 per hour
• LeMUR – varies
• Enterprise pricing is also available

See the full pricing list here .

• High accuracy
• Breadth of AI models available, built by AI experts
• Continuous model iteration and improvement
• Developer-friendly documentation and SDKs
• Enterprise-grade support and security
• Models are not open-source

Google Speech-to-Text is a well-known speech transcription API. Google gives users 60 minutes of free transcription, with $300 in free credits for Google Cloud hosting.

Google only supports transcribing files already in a Google Cloud Bucket, so the free credits won’t get you very far. Google also requires you to sign up for a GCP account and project — whether you're using the free tier or paid.

With good accuracy and 125+ languages supported, Google is a decent choice if you’re willing to put in some initial work.

• 60 minutes of free transcription
• $300 in free credits for Google Cloud hosting
• Decent accuracy
• Multi-language support
• Only supports transcription of files in a Google Cloud Bucket
• Difficult to get started
• Lower accuracy than other similarly-priced APIs
• AWS Transcribe

AWS Transcribe offers one hour free per month for the first 12 months of use.

Like Google, you must create an AWS account first if you don’t already have one. AWS also has lower accuracy compared to alternative APIs and only supports transcribing files already in an Amazon S3 bucket.

However, if you’re looking for a specific feature, like medical transcription, AWS has some options. Its Transcribe Medical API is a medical-focused ASR option that is available today.

• One hour free per month for the first 12 months of use
• Tiered pricing , based on usage, ranges from $0.02400 to $0.00780
• Integrates into existing AWS ecosystem
• Medical language transcription
• Difficult to get started from scratch
• Only supports transcribing files already in an Amazon S3 bucket

Open-Source Speech Transcription engines

An alternative to APIs and AI models, open-source Speech-to-Text libraries are completely free--with no limits on use. Some developers also see data security as a plus, since your data doesn’t have to be sent to a third party or the cloud.

There is work involved with open-source engines, so you must be comfortable putting in a lot of time and effort to get the results you want, especially if you are trying to use these libraries at scale. Open-source Speech-to-Text engines are typically less accurate than the APIs discussed above.

If you want to go the open-source route, here are some options worth exploring:

DeepSpeech is an open-source embedded Speech-to-Text engine designed to run in real-time on a range of devices, from high-powered GPUs to a Raspberry Pi 4. The DeepSpeech library uses end-to-end model architecture pioneered by Baidu.

DeepSpeech also has decent out-of-the-box accuracy for an open-source option and is easy to fine-tune and train on your own data.

• Easy to customize
• Can use it to train your own model
• Can be used on a wide range of devices
• Lack of support
• No model improvement outside of individual custom training
• Heavy lift to integrate into production-ready applications

Kaldi is a speech recognition toolkit that has been widely popular in the research community for many years.

Like DeepSpeech, Kaldi has good out-of-the-box accuracy and supports the ability to train your own models. It’s also been thoroughly tested—a lot of companies currently use Kaldi in production and have used it for a while—making more developers confident in its application.

• Can use it to train your own models
• Active user base
• Can be complex and expensive to use
• Uses a command-line interface

Flashlight ASR (formerly Wav2Letter)

Flashlight ASR, formerly Wav2Letter, is Facebook AI Research’s Automatic Speech Recognition (ASR) Toolkit. It is also written in C++ and usesthe ArrayFire tensor library.

Like DeepSpeech, Flashlight ASR is decently accurate for an open-source library and is easy to work with on a small project.

• Customizable
• Easier to modify than other open-source options
• Processing speed
• Very complex to use
• No pre-trained libraries available
• Need to continuously source datasets for training and model updates, which can be difficult and costly
• SpeechBrain

SpeechBrain is a PyTorch-based transcription toolkit. The platform releases open implementations of popular research works and offers a tight integration with Hugging Face for easy access.

Overall, the platform is well-defined and constantly updated, making it a straightforward tool for training and finetuning.

• Integration with Pytorch and Hugging Face
• Pre-trained models are available
• Supports a variety of tasks
• Even its pre-trained models take a lot of customization to make them usable
• Lack of extensive docs makes it not as user-friendly, except for those with extensive experience

Coqui is another deep learning toolkit for Speech-to-Text transcription. Coqui is used in over twenty languages for projects and also offers a variety of essential inference and productionization features.

The platform also releases custom-trained models and has bindings for various programming languages for easier deployment.

• Generates confidence scores for transcripts
• Large support comunity
• No longer updated and maintained by Coqui

Whisper by OpenAI, released in September 2022, is comparable to other current state-of-the-art open-source options.

Whisper can be used either in Python or from the command line and can also be used for multilingual translation.

Whisper has five different models of varying sizes and capabilities, depending on the use case, including v3 released in November 2023 .

However, you’ll need a fairly large computing power and access to an in-house team to maintain, scale, update, and monitor the model to run Whisper at a large scale, making the total cost of ownership higher compared to other options. 

As of March 2023, Whisper is also now available via API . On-demand pricing starts at $0.006/minute.

• Multilingual transcription
• Can be used in Python
• Five models are available, each with different sizes and capabilities
• Need an in-house research team to maintain and update
• Costly to run

Which free Speech-to-Text API, AI model, or Open Source engine is right for your project?

The best free Speech-to-Text API, AI model, or open-source engine will depend on our project. Do you want something that is easy-to-use, has high accuracy, and has additional out-of-the-box features? If so, one of these APIs might be right for you:

Alternatively, you might want a completely free option with no data limits—if you don’t mind the extra work it will take to tailor a toolkit to your needs. If so, you might choose one of these open-source libraries:

Whichever you choose, make sure you find a product that can continually meet the needs of your project now and what your project may develop into in the future.

Want to get started with an API?

Get a free API key for AssemblyAI.

Popular posts

Announcements

Claude 3 Models now available with LeMUR

Head of Product Marketing

Build Powerful Speech AI Apps with AssemblyAI and LLM Integrations

Developer Educator

Create Multi-Lingual Subtitles with AssemblyAI and DeepL

Featured writer

Build an AI-powered video conferencing app with Next.js and Stream

Senior Developer Advocate, Developer Advocate at Stream

Text to speech in the browser with the Web Speech API

Time to read: 5 minutes

• Facebook logo
• Twitter Logo Follow us on Twitter
• LinkedIn logo

The Web Speech API has two functions, speech synthesis , otherwise known as text to speech, and speech recognition . With the SpeechSynthesis API we can command the browser to read out any text in a number of different voices.

From a vocal alerts in an application to bringing an Autopilot powered  chatbot to life on your website, the Web Speech API has a lot of potential for web interfaces. Follow on to find out how to get your web application speaking back to you.

What you'll need

If you want to build this application as we learn about the SpeechSynthesis API then you'll need a couple of things:

• A modern browser ( the API is supported across the majority of desktop and mobile browsers )
• A text editor

Once you're ready, create a directory to work in and download this HTML file  and this CSS file  to it. Make sure they are in the same folder and the CSS file is named style.css . Open the HTML file in your browser and you should see this:

Let's get started with the API by getting the browser to talk to us for the first time.

The Speech Synthesis API

Before we start work with this small application, we can get the browser to start speaking using the browser's developer tools. On any web page, open up the developer tools console and enter the following code:

Your browser will speak the text " Hello, this is your browser speaking. " in its default voice. We can break this down a bit though.

We created a SpeechSynthesisUtterance which contained the text we wanted to be spoken. Then we passed the utterance to the speak method of the speechSynthesis object. This queues up the utterance to be spoken and then starts the browser speaking. If you send more than one utterance to the speak method they will be spoken one after another.

Let's take the starter code we downloaded earlier and turn this into a small app where we can input the text to be spoken and choose the voice that the browser says it in.

Speech Synthesis in a web application

Open up the HTML file you downloaded earlier in your text editor. We'll start by connecting the form up to speak whatever you enter in the text input when you submit. Later, we'll add the ability to choose the voice to use.

Between the <script> tags at the bottom of the HTML we'll start by listening for the DOMContentLoaded event and then selecting some references to the elements we'll need.

We then need to listen to the submit event on the form and when it fires, grab the text from the input. With that text we'll create a SpeechSynthesisUtterance and then pass it to speechSynthesis.speak . Finally, we empty the input box and wait for the next thing to say.

Open the HTML in your browser and enter some text in the input. You can ignore the <select> box at this point, we'll use that in the next section. Hit " Say it " and listen to the browser read out your words.

It's not much code to get the browser to say something, but what if we want to pick the voice that it uses. Let's populate the dropdown on the page with the available voices and use it to select the one we want to use.

Picking voices for text to speech

We need to get references to the <select> element on the page and initialise a couple of variables we'll use to store the available voices and the current voice we are using. Add this to the top of the script:

Next up we need to populate the select element with the available voices. We'll create a new function to do this, as we might want to call it more than once (more on that in a bit). We can call on speechSynthesis.getVoices() to return the available SpeechSynthesisVoice objects .

Whilst we are populating the voice options we should also detect the currently selected voice. If we have already chosen a voice we can check against our currentVoice object and if we haven't yet chosen a voice then we can detect the default voice with the voice.default property.

We can call populateVoice straight away. Some browsers will load the voices page load and will return their list straight away. Other browsers need to load their list of voices asynchronously and will emit a "voiceschanged" event once they have loaded. Some browsers do not emit this event at all though.

To account for all the potential scenarios we'll call populateVoices immediately and also set it as the callback to the "voiceschanged" event.

Reload the page and you will see the <select> element populated with all the available voices, including the language the voice supports. We haven't hooked up selecting and using the voice yet though, that comes next.

Listen to the "change" event of the select element and whenever it is fired, select the currentVoice using the selectedIndex of the <select> element.

Now, to use the voice with the speech utterance we need to set the voice on the utterance that we create.

Reload the page and play around selecting different voices and saying different things.

Bonus: build a visual speaking indicator

We've built a speech synthesiser that can use different voices, but I wanted to throw one more thing in for fun. Speech utterances emit a number of events  that you can use to make your application respond to speech. To finish this little app off we're going to make an animation show as the browser is speaking. I've already added the CSS for the animation  so to activate it we need to add a "speaking" class to the <main> element while the browser is speaking.

Grab a reference to the <main> element at the top of the script:

Now, we can listen to the start and end events of the utterance to add and remove the "speaking" class. But, if we remove the class in the middle of the animation it won't fade out smoothly, so we should listen for the end of the animation's iteration, using the "animationiteration" event , and then remove the class.

Now when you start the browser talking the background will pulse blue and when the utterance is over it will stop.

Your browser is getting chatty

In this post you've seen how to get started and work with the Speech Synthesis API  from the Web Speech API . All the code for this application can be found on GitHub  and you can see it in action or remix it on Glitch .

I'm excited about the potential of this API for building my own in browser bots, so look out for more of this in the future.

Have you used the Speech Synthesis API or have any plans for it? I'd love to hear in the comments below, or drop me a note at philnash@twilio.com  or on Twitter at @philnash .

Related Posts

Related Resources

Twilio docs, from apis to sdks to sample apps.

API reference documentation, SDKs, helper libraries, quickstarts, and tutorials for your language and platform.

Resource Center

The latest ebooks, industry reports, and webinars.

Learn from customer engagement experts to improve your own communication.

Twilio's developer community hub

Best practices, code samples, and inspiration to build communications and digital engagement experiences.

This browser is no longer supported.

Upgrade to Microsoft Edge to take advantage of the latest features, security updates, and technical support.

Speech to text REST API

• 3 contributors

Speech to text REST API is used for batch transcription and custom speech .

Speech to text REST API v3.2 is the latest version that's generally available. Preview versions 3.2-preview.1 and 3 .2-preview.2* will be removed in September 2024. Speech to text REST API v3.1 will be retired on a date to be announced. For more information about upgrading, see the Speech to text REST API v3.1 to v3.2 migration guide. Speech to text REST API v3.0 will be retired on April 1st, 2026. For more information about upgrading, see the Speech to text REST API v3.0 to v3.1 and v3.1 to v3.2 migration guides.

See the Speech to text REST API v3.2 reference documentation

See the Speech to text REST API v3.1 reference documentation

See the Speech to text REST API v3.0 reference documentation

Use Speech to text REST API to:

• Custom speech : With custom speech, you can upload your own data, test and train a custom model, compare accuracy between models, and deploy a model to a custom endpoint. Copy models to other subscriptions if you want colleagues to have access to a model that you built, or if you want to deploy a model to more than one region.
• Batch transcription : Transcribe audio files as a batch from multiple URLs or an Azure container.

Speech to text REST API includes such features as:

• Get logs for each endpoint if logs are requested for that endpoint.
• Request the manifest of the models that you create, to set up on-premises containers.
• Upload data from Azure storage accounts by using a shared access signature (SAS) URI.
• Bring your own storage. Use your own storage accounts for logs, transcription files, and other data.
• Some operations support webhook notifications. You can register your webhooks where notifications are sent.

Batch transcription

The following operation groups are applicable for batch transcription .

Custom speech

The following operation groups are applicable for custom speech .

Service health

Service health provides insights about the overall health of the service and subcomponents. See Service Health for more information.

• Create a custom speech project
• Get familiar with batch transcription

Was this page helpful?

Coming soon: Throughout 2024 we will be phasing out GitHub Issues as the feedback mechanism for content and replacing it with a new feedback system. For more information see: https://aka.ms/ContentUserFeedback .

Submit and view feedback for

Additional resources

The Best Speech-to-Text APIs in 2024

If you've been shopping for a speech-to-text (STT) solution for your business, you're not alone. In our recent  State of Voice Technology  report, 82% of respondents confirmed their current utilization of voice-enabled technology, a 6% increase from last year.

The vast number of options for speech transcription can be overwhelming, especially if you're unfamiliar with the space. From Big Tech to open source options, there are many choices, each with different price points and feature sets. While this diversity is great, it can also be confusing when you're trying to compare options and pick the right solution.

This article breaks down the leading speech-to-text APIs available today, outlining their pros and cons and providing a ranking that accurately represents the current STT landscape. Before getting to the ranking, we explain exactly what an STT API is, and the core features you can expect an STT API to have, and some key use cases for speech-to-text APIs.

What is a speech-to-text API?

At its core, a speech-to-text (also known as automatic speech recognition, or ASR) application programming interface (API) is simply the ability to call a service to transcribe audio containing speech into written text. The STT service will take the provided audio data, process it using either machine learning or legacy techniques (e.g. Hidden Markov Models), and then provide a transcript of what it has inferred was said.

What are the most important things to consider when choosing a speech-to-text API?

What makes the best speech-to-text API? Is the fastest speech-to-text API the best? Is the most accurate speech-to-text API the best? Is the most affordable speech-to-text API the best? The answers to these questions depend on your specific project and are thus certainly different for everybody. There are a number of aspects to carefully consider in the evaluation and selection of a transcription service and the order of importance is dependent on your target use case and end user needs.

Accuracy - A speech-to-text API should produce highly accurate transcripts, even while dealing with varying levels of speaking conditions (e.g. background noise, dialects, accents, etc.). “Garbage in, garbage out,” as the saying goes. The vast majority of voice applications require highly accurate results from their transcription service to deliver value and a good customer experience to their users.

Speed - Many applications require quick turnaround times and high throughput. A responsive STT solution will deliver value with low latency and fast processing speeds.

Cost - Speech-to-text is a foundational capability in the application stack, and cost efficiency is essential. Solutions that fail to deliver adequate ROI and a good price-to-performance ratio will be a barrier to the overall utility of the end user application.

Modality - Important input modes include support for pre-recorded or real-time audio:

Batch or pre-recorded transcription capabilities - Batch transcription won't be needed by everyone, but for many use cases, you'll want a service that you can send batches of files to to be transcribed, rather than having to do it one-by-one on your end.

Real-time streaming - Again, not everyone will need real-time streaming. However, if you want to use STT to create, for example, truly conversational AI that can respond to customer inquiries in real time, you'll need to use a STT API that returns its results as quickly as possible.

Features & Capabilities - Developers and companies seeking speech processing solutions require more than a bare transcript. They also need rich features that help them build scalable products with their voice data, including sophisticated formatting and speech understanding capabilities to improve readability and utility by downstream tasks.

Scalability and Reliability - A good speech-to-text solution will accommodate varying throughput needs, adequately handling a range of audio data volumes from small startups to large enterprises. Similarly, ensuring reliable, operational integrity is a hard requirement for many applications where the effects from frequent or lengthy service interruption could result in revenue impacts and damage to brand reputation. 

Customization, Flexibility, and Adaptability - One size, fits few. The ability to customize STT models for specific vocabulary or jargon as well as flexible deployment options to meet project-specific privacy, security, and compliance needs are important, often overlooked considerations in the selection process.

Ease of Adoption and Use - A speech-to-text API only has value if it can be integrated into an application. Flexible pricing and packaging options are critical, including usage-based pricing with volume discounts. Some vendors do a better job than others to provide a good developer experience by offering frictionless self-onboarding and even including free tiers with an adequate volume of credits to help developers test the API and prototype their applications before choosing the best subscription option to choose.

Support and Subject Matter Expertise - Domain experts in AI, machine learning, and spoken language understanding are an invaluable resource when issues arise. Many solution providers outsource their model development or offer STT as a value-add to their core offering. Vendors for whom speech AI is their core focus are better equipped to diagnose and resolve challenge issues in a timely fashion. They are also more inclined to make continuous improvements to their STT service and avoid issues with stagnating performance over time.

What are the most important features of a speech-to-text API?

In this section, we'll survey some of the most common features that STT APIs offer. The key features that are offered by each API differ, and your use cases will dictate your priorities and needs in terms of which features to focus on.

Multi-language support - If you're planning to handle multiple languages or dialects, this should be a key concern. And even if you aren't planning on multilingual support now, if there's any chance that you would in the future, you're best off starting with a service that offers many languages and is always expanding to more.

Formatting - Formatting options like punctuation, numeral formatting, paragraphing, speaker labeling (or speaker diarization), word-level timestamping, profanity filtering, and more, all to improve readability and utility for data science

Automatic punctuation & capitalization - Depending on what you're planning to do with your transcripts, you might not care if they're formatted nicely. But if you're planning on surfacing them publicly, having this included in what the STT API provides can save you time.

Profanity filtering or redaction - If you're using STT as part of an effort for community moderation, you're going to want a tool that can automatically detect profanity in its output and censor it or flag it for review.

Understanding - A primary motivation for employing a speech-to-text API is to gain understanding of who said what and why they said it. Many applications employ natural language and spoken language understanding tasks to accurately identify, extract, and summarize conversational audio to deliver amazing customer experiences. 

Topic detection - Automatically identify the main topics and themes in your audio to improve categorization, organization, and understanding of large volumes of spoken language content..

Intent detection - Similarly, intent detection is used to determine the purpose or intention behind the interactions between speakers, enabling more efficient handling by downstream agents or tasks in a system in order to determine the next best action to take or response to provide.

Sentiment analysis - Understand the interactions, attitudes, views, and emotions in conversational audio by quantitatively scoring the overall and component sections as being positive, neutral, or negative. 

Summarization - Deliver a concise summary of the content in your audio, retaining the most relevant and important information and overall meaning, for responsive understanding, analysis, and efficient archival.

Keywords (a.k.a. Keyword Boosting) - Being able to include an extended, custom vocabulary is helpful if your audio has lots of specialized terminology, uncommon proper nouns, abbreviations, and acronyms that an off-the-shelf model wouldn't have been exposed to. This allows the model to incorporate these custom terms as possible predictions.

Custom models - While keywords provide inclusion of a small set of specialized, out-of-vocabulary words, a custom model trained on representative data will always give the best performance. Vendors that allow you to tailor a model for your specific needs, fine-tuned on your own data, give you the ability to boost accuracy beyond what an out-of-the-box solution alone provides.

Accepts multiple audio formats - Another concern that won't be present for everyone is whether or not the STT API can process audio in different formats. If you have audio coming from multiple sources that aren't encoded in the same format, having a STT API that removes the need for converting to different types of audio can save you time and money.

What are the top speech-to-text use cases?

As noted at the outset, voice technology that's built on the back of STT APIs is a critical part of the future of business. So what are some of the most common use cases for speech-to-text APIs? Let's take a look.

Smart assistants  - Smart assistants like Siri and Alexa are perhaps the most frequently encountered use case for speech-to-text, taking spoken commands, converting them to text, and then acting on them.

Conversational AI  - Voicebots let humans speak and, in real time, get answers from an AI. Converting speech to text is the first step in this process, and it has to happen quickly for the interaction to truly feel like a conversation.

Sales and support enablement  - Sales and support digital assistants that provide tips, hints, and solutions to agents by transcribing, analyzing and pulling up information in real time. It can also be used to gauge sales pitches or sales calls with a customer.

Contact centers  - Contact centers can use STT to create transcripts of their calls, providing more ways to evaluate their agents, understand what customers are asking about, and provide insight into different aspects of their business that are typically hard to assess.

Speech analytics  - Broadly speaking, speech analytics is any attempt to process spoken audio to extract insights. This might be done in a call center, as above, but it could also be done in other environments, like meetings or even speeches and talks.

Accessibility  - Providing transcriptions of spoken speech can be a huge win for accessibility, whether it's  providing captions for classroom lectures  or creating badges that transcribe speech on the fly.

How do you evaluate performance of a speech-to-text API?

All speech-to-text solutions aim to produce highly accurate transcripts in a user-friendly format. We advise performing side-by-side accuracy testing using files that resemble the audio you will be processing in production to determine the best speech solution for your needs. The best evaluation regimes employ a holistic approach that includes a mix of quantitative benchmarking and qualitative human preference evaluation across the most important dimensions of quality and performance, including accuracy and speed.

The generally accepted industry metric for measuring transcription quality is Word Error Rate (WER). Consider WER in relation to the following equation:

WER + Accuracy Rate = 100%

Thus, an 80% accurate transcript corresponds to a WER of 20%

WER is an industry standard focusing on error rate rather than accuracy as the error rate can be subdivided into distinct error categories. These categories provide valuable insights into the nature of errors present in a transcript. Consequently, WER can also be defined using the formula:

WER = (# of words inserted + # of words deleted + # of words substituted) / total # of words.

We suggest a degree of skepticism towards vendor claims about accuracy. This includes the qualitative claim that OpenAI’s model “approaches human level robustness on accuracy in English,” and the WER statistics published in Whisper’s documentation.

Highest Fastest Lowest High High Slow Low Low High Slow High Medium Medium Very slow High Medium Medium Medium Medium Medium High Medium High Low High Very slow High Medium High Medium High Medium Low Slow High Medium Low Slow Low Medium

There you have it–the top 10 speech-to-text APIs in 2024. We hope that this helps you demystify some of the confusion around the proliferation of options that exist in this space, and gives you a better sense of which provider might be the best for your particular use case. If you'd like to give Deepgram a try for yourself, you can sign up for a free API key or contact us if you have questions about how you might use Deepgram for your transcription needs. If you have any feedback about this post, or anything else around Deepgram, we'd love to hear from you. Please let us know in our   GitHub discussions  or  contact us  to talk to one of our product experts for more information today.

Unlock language AI at scale with an API call.

Get conversational intelligence with transcription and understanding on the world's best speech AI platform.

Text to Speech API Python: A Comprehensive Guide

Looking for our  Text to Speech Reader ?

Featured In

Table of contents, prerequisites, installing dependencies, google cloud text-to-speech setup, using google cloud text-to-speech, using gtts (google text-to-speech), real-time text-to-speech, language support, audio encoding, configuring voice parameters, linux and windows, source code and documentation.

Text-to-speech ( TTS ) technology has significantly advanced, allowing developers to create high-quality audio from text inputs using various programming languages, including Python. This article will guide you through the process of setting up and using a TTS API in Python, covering installation, configuration, and usage with code examples. We will explore various APIs, including Google Cloud Text-to-Speech and open-source alternatives like gTTS. Whether you need English, French, German, Chinese, or Hindi, this tutorial has got you covered.

Before we start, ensure you have Python 3 installed on your system. You can download it from the official Python website . Additionally, you'll need pip, the Python package installer, which is included with Python 3.

To begin, you'll need to install the required Python libraries. Open your command-line interface (CLI) and run the following command:

These libraries will allow you to interact with the Google Cloud Text-to-Speech API and the open-source gTTS library.

• Step 1 : Create a Google Cloud Project: First, create a project on the Google Cloud Console .
• Step 2 : Enable the Text-to-Speech API: Navigate to the API Library and enable the Google Cloud Text-to-Speech API.
• Step 3 : Create Service Account and API Key: Create a service account and download the JSON key file. Set the GOOGLE_APPLICATION_CREDENTIALS environment variable to point to this file:

Here's a "Hello World" example using the Google Cloud Text-to-Speech API:

This code synthesizes speech from text and saves it as an MP3 file.

For a simpler and open-source alternative, you can use gTTS. Here's a basic example:

To achieve real-time TTS, you can integrate the TTS API with applications that require instant feedback, such as voice assistants or chatbots.

Advanced Configuration and Parameters

Google Cloud Text-to-Speech supports various languages, including English (en-US), French (fr-FR), German (de-DE), Chinese (zh-CN), and Hindi (hi-IN). You can change the language_code parameter in the synthesize_text function to use different languages.

The audio_encoding parameter supports different formats such as MP3, WAV, and FLAC. Modify the AudioConfig accordingly.

You can customize voice parameters such as pitch, speaking rate, and volume gain. For example:

Using the TTS API with Other Platforms

You can integrate the TTS API with Android applications using HTTP requests to the Google Cloud Text-to-Speech API.

The provided Python examples work seamlessly on both Linux and Windows platforms.

Find the complete source code and detailed documentation on GitHub and Google Cloud Text-to-Speech documentation .

In this tutorial, we've covered the basics of setting up and using Text-to-Speech APIs in Python, including Google Cloud Text-to-Speech and gTTS. Whether you need high-quality speech synthesis for English, French, German, Chinese, or Hindi, these tools provide robust solutions. Explore further configurations and parameters to enhance your applications and achieve real-time TTS integration.

By following this guide, you should now be able to convert text to high-quality audio files using Python, enabling you to create engaging and accessible applications.

The free text-to-speech API for Python is gTTS (Google Text-to-Speech), an open-source library that allows you to convert text to speech using Google's TTS API.

Yes, Python can perform text-to-speech using libraries such as gTTS and the Google Cloud Text-to-Speech API, which utilize speech recognition and artificial intelligence technologies.

To use Google Text to Speech API in Python, install the client library, set up your API key, and use the texttospeech SDK to synthesize speech; refer to the quickstart guide for detailed steps.

Google Text to Speech API offers a free tier with limited usage, but for extensive use, pricing terms apply; it provides low latency and high-quality speech synthesis suitable for various machine learning and artificial intelligence applications.

Celebrity Voice Generators: A How to

Read Aloud: Transforming the Way We Experience Text

Cliff Weitzman

Cliff Weitzman is a dyslexia advocate and the CEO and founder of Speechify, the #1 text-to-speech app in the world, totaling over 100,000 5-star reviews and ranking first place in the App Store for the News & Magazines category. In 2017, Weitzman was named to the Forbes 30 under 30 list for his work making the internet more accessible to people with learning disabilities. Cliff Weitzman has been featured in EdSurge, Inc., PC Mag, Entrepreneur, Mashable, among other leading outlets.

• Español – América Latina
• Português – Brasil
• Cloud Speech-to-Text
• Documentation

Cloud Speech-to-Text API

Converts audio to text by applying powerful neural network models.

REST Resource: v1p1beta1.operations

Rest resource: v1p1beta1.projects.locations.customclasses, rest resource: v1p1beta1.projects.locations.phrasesets, rest resource: v1p1beta1.speech, rest resource: v1.operations, rest resource: v1.projects.locations.customclasses, rest resource: v1.projects.locations.phrasesets, rest resource: v1.speech, service: speech.googleapis.com.

To call this service, we recommend that you use the Google-provided client libraries . If your application needs to use your own libraries to call this service, use the following information when you make the API requests.

Discovery document

A Discovery Document is a machine-readable specification for describing and consuming REST APIs. It is used to build client libraries, IDE plugins, and other tools that interact with Google APIs. One service may provide multiple discovery documents. This service provides the following discovery documents:

• https://speech.googleapis.com/$discovery/rest?version=v1
• https://speech.googleapis.com/$discovery/rest?version=v1p1beta1

Service endpoint

A service endpoint is a base URL that specifies the network address of an API service. One service might have multiple service endpoints. This service has the following service endpoint and all URIs below are relative to this service endpoint:

• https://speech.googleapis.com

Methods
	Starts asynchronous cancellation on a long-running operation.
	Deletes a long-running operation.
	Gets the latest state of a long-running operation.
	Lists operations that match the specified filter in the request.

Methods
	Create a custom class.
	Delete a custom class.
	Get a custom class.
	List custom classes.
	Update a custom class.

Methods
	Create a set of phrase hints.
	Delete a phrase set.
	Get a phrase set.
	List phrase sets.
	Update a phrase set.

Methods
	Performs asynchronous speech recognition: receive results via the google.longrunning.Operations interface.
	Performs synchronous speech recognition: receive results after all audio has been sent and processed.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License , and code samples are licensed under the Apache 2.0 License . For details, see the Google Developers Site Policies . Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2023-01-26 UTC.