A Deepgram client for Dart and Flutter, supporting all Speech-to-Text and Text-to-Speech features on every platform.

You need something else ? Feel free to create issues, contribute to this project or to ask for new features on GitHub !

Features

Speech-to-Text	Status	Methods
From File	✅	listen.file(), listen.path()
From URL	✅	listen.url()
From Byte	✅	listen.bytes()
From Audio Stream	✅	listen.live(), listen.liveListener()

Text-to-Speech	Status	Methods
From Text	✅	speak.text()
From Text Stream	✅	speak.live(), speak.liveSpeaker()

Agent Interaction	Status	Methods
Agent Interaction	🚧	agent.live()

PRs are welcome for all work-in-progress 🚧 features

Getting started

All you need is a Deepgram API key. You can get a free one by signing up on Deepgram

Usage

First create the client with optional parameters

String apiKey = 'your_api_key';

// you can pass params in client's baseQueryParams or in every method's queryParams
Deepgram deepgram = Deepgram(apiKey, baseQueryParams: {
  'model': 'nova-2-general',
  'detect_language': true,
  'filler_words': false,
  'punctuation': true,
  // more options here : https://developers.deepgram.com/reference/listen-file
});

Then you can call the methods you need under the propper listen or speak subclass:

// Speech to text
DeepgramListenResult res = await deepgram.listen.file(File('audio.wav'));

// Text to speech
DeepgramSpeakResult res = await deepgram.speak.text('Hello world');

STT Result

All STT methods return a DeepgramListenResult object with the following properties :

class DeepgramListenResult {
  final String json; // raw json response
  final Map<String, dynamic> map; // parsed json response into a map
  final String? transcript; // the transcript extracted from the response
  final String? type; // the response type (Result, Metadata, ...) non-null for streaming
}

TTS Result

All TTS methods return a DeepgramSpeakResult object with the following properties :

class DeepgramSpeakResult {
  final Uint8List? data; // raw audio data
  final Map<String, dynamic>? metadata; /// The headers or metadata if streaming
}

Streaming

Speech to text

let's say from a microphone :

//  https://pub.dev/packages/record (other packages would work too)
Stream<List<int>> micStream = await AudioRecorder().startStream(RecordConfig(
      encoder: AudioEncoder.pcm16bits,
      sampleRate: 16000,
      numChannels: 1,
));

final streamParams = {
  'detect_language': false, // not supported by streaming API
  'language': 'en',
  // must specify encoding and sample_rate according to the audio stream
  'encoding': 'linear16',
  'sample_rate': 16000,
};

Deepgram deepgram = Deepgram(apiKey, baseQueryParams: streamParams);

then you got 2 options depending if you want to have more control over the stream or not :

// 1. you want the stream to manage itself automatically
Stream<DeepgramListenResult> stream = deepgram.listen.live(micStream);

// 2. you want to manage the stream manually
DeepgramLiveListener listener = deepgram.liveListener(micStream);
listener.stream.listen((res) {
    print(res.transcript);
});
// connect to the servers and start sending data
listener.start();

// you can pause and resume the transcription (stop sending audio data to the server)
listener.pause(); 
// ...
listener.resume();

// then close the stream when you're done, you can call start() again if you want to restart a transcription 
listener.close(); 

Text to speech

Deepgram deepgram = Deepgram(apiKey, baseQueryParams: {
  'model': 'aura-asteria-en',
  'encoding': "linear16",
  'sample_rate': 16000,
// options here: https://developers.deepgram.com/reference/text-to-speech-api
});

then again you got 2 options:

final textStream = ...
// 1. you want the stream to manage itself automatically
Stream<DeepgramSpeakResult> stream = deepgram.speak.live(textStream);

// 2. you want to manage the stream manually
DeepgramLiveSpeaker speaker = deepgram.liveListener(textStream);
speaker.stream.listen((res) {
    print(res);
    // if you want to use the audio, simplest way is to use Deepgram.toWav(res.data) !
});

// start sending data to the servers
speaker.start();

// https://developers.deepgram.com/docs/tts-ws-flush 
speaker.flush();

//https://developers.deepgram.com/docs/tts-ws-clear
speaker.clear();

// then close the stream when you're done, you can call start() again if you want to restart a transcription 
speaker.close(); 

For more detailed usage check the /example tab

• Flutter demo here

• Dart demo here

Tested on Android and iOS, but should work on other platforms too.

Debugging common errors

• make sure your API key is valid and has enough credits

deepgram.isApiKeyValid()

• "Websocket was not promoted ..." : you are probably using wrong parameters, for example trying to use a whisper model with live streaming (not supported by deepgram)
• empty transcript/only metadata : if streaming check that you specified encoding and sample_rate properly and that it matches the audio stream
• double check the parameters you are using, some are not supported for streaming or for some models

Additional information

I created this package for my own needs since there are no dart sdk for deepgram. Happy to share !

Don't hesitate to ask for new features or to contribute on GitHub !

Support

If you'd like to support this project, consider contributing here. Thank you! :)