transcribe_cpp

pub package CI platforms license: MIT

Offline speech-to-text for Flutter. The user talks, your app gets text, and the audio never leaves the phone.

Run Whisper, Parakeet, Moonshine and more than 50 other open speech models on the phone, in about 100 languages. The speech recognition comes from transcribe.cpp; this package brings it to Flutter, with microphone capture, voice detection (Silero VAD) and live text around it.

A reading transcribed live on the phone in airplane mode: the sentence in progress appears in a Live box, finished sentences below it

  • Private. Everything runs on the device: no server, no account, no API key.
  • Hands-free. Voice detection decides when each sentence ends. No button to hold.
  • Live text. Words appear while the user is still speaking, and settle in place without flickering.
  • Fast. About 40 times faster than real time on a mid-range phone.
  • Your choice of model. Whisper for about 100 languages, Parakeet for the best English accuracy, Moonshine for the smallest download.
  • Resilient. Keeps going through calls, Siri, headphones being plugged in, and the app going to the background.
  • Your audio, too. Already record audio yourself? Feed it in at any sample rate.

Install

flutter pub add transcribe_cpp

Then let your app use the microphone. On iOS, add a reason to ios/Runner/Info.plist:

<key>NSMicrophoneUsageDescription</key>
<string>Your speech is transcribed on this device.</string>

On Android, add to android/app/src/main/AndroidManifest.xml:

<uses-permission android:name="android.permission.RECORD_AUDIO"/>
<uses-permission android:name="android.permission.INTERNET"/>

Use it

import 'package:transcribe_cpp/transcribe_cpp.dart';

// Download a model once (90 MB). Later calls return it straight away.
final models = await ModelManager.open();
final model = await models.ensure(const ModelId('parakeet-tdt_ctc-110m-Q4_K_M'));

// Load it, and listen.
final session = await TranscribeSession.open(model);
await session.start();

// Show the text as the user speaks.
ValueListenableBuilder(
  valueListenable: session.text,
  builder: (context, text, _) => Text(text.full),
);

await session.stop();

Already capture audio yourself? Hand it over instead of using the microphone:

await session.transcribeStream(
  myAudio,
  format: const AudioFormat(sampleRate: 48000),
);

Models

Models are downloaded at runtime, not bundled with your app. Good places to start:

Model Download Languages Word error rate*
parakeet-tdt_ctc-110m-Q4_K_M 90 MB English 2.5%
moonshine-streaming-tiny-Q8_0 50 MB English 4.5%
whisper-base-Q8_0 81 MB 99 5.1%

* LibriSpeech test-clean (English), from the models' published benchmarks.

The catalogue has 58 models in all, from Whisper, Parakeet, Canary, Moonshine, SenseVoice, Qwen3-ASR and other families: every model transcribe.cpp publishes up to 1 GB.

Platforms

iOS 16.0 or later. Runs on the GPU.
Android 7.0 (API 24) or later, 64-bit. Runs on the CPU.

Documentation

The full guide is at ishangavidusha.github.io/transcribe_cpp: choosing and downloading models, live text and sentences, interruptions, listening in the background, tuning, and how it all works.

The example app is a complete app with a model picker.

Contributing

Bug reports, ideas and pull requests are welcome. See CONTRIBUTING.md.

Acknowledgements

transcribe_cpp stands on the work of others:

  • transcribe.cpp by the transcribe.cpp authors, the engine that runs the models, and the source of the model catalogue and the converted models on Hugging Face.
  • ggml, the machine-learning library underneath it.
  • Silero VAD, the voice detector, ported to C for this package.
  • The model authors, including NVIDIA for Parakeet and the Moonshine team for Moonshine.

transcribe_cpp is an independent project, not an official part of transcribe.cpp.

License

MIT. The package includes builds of transcribe.cpp and ggml, and weights derived from Silero VAD, all MIT; see THIRD-PARTY-LICENSES.md.

Speech models are downloaded by your app and carry their own licences, and some are non-commercial. Parakeet, for example, is CC-BY-4.0, which asks apps that use it to credit NVIDIA. Check ModelDescriptor.license for each model you ship.

Libraries

transcribe_cpp
Offline, on-device speech-to-text for Flutter, over transcribe.cpp, a ggml/GGUF speech engine, with Metal acceleration on iOS.