coqui-ai / STT-examples

🐸STT integration examples

Coqui STT 1.0.x Examples

These are various examples on how to use or integrate 🐸STT using our packages.

It is a good way to just try out 🐸STT before learning how it works in detail, as well as a source of inspiration for ways you can integrate it into your application or solve common tasks like voice activity detection (VAD) or microphone streaming.

Contributions are welcome!

Note: These examples target 🐸STT 1.0.x only. If you're using a different release, you need to go to the corresponding branch for the release:

• v1.0.x
• v0.9.x
• v0.8.x
• v0.7.x
• v0.6.x
• main branch

List of examples

Python:

• Microphone VAD streaming
• VAD transcriber
• Websocket-based server
• Django streaming API

JavaScript:

• FFMPEG VAD streaming
• Node.JS microphone VAD streaming
• Node.JS wav
• Web Microphone Websocket streaming
• Electron wav transcriber
• Client-side, fully offline WebAssembly audio transcriber

Windows/C#:

• .NET framework
• Universal Windows Platform (UWP).

Java/Android:

• mozilla/androidspeech library

Nim:

• nim_mic_vad_streaming.

Help + Community

1. Github Discussions - find and join open-ended community discussions related to 🐸STT-examples
2. Gitter Chat - the 🐸 Gitter rooms where you can chat with folks about 🐸STT-examples, get help, share ideas :)
3. Github Issues - If you ran into a specific error/problem, feel free to open an issue in the repo.