#148 · Primary category: Speech & Audio

whisper-playground

machine-learning openai speech-recognition speech-to-text whisper

Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/

Project last updated:09/12/25

GitHub Stars

835

Forks

143

Contributors

3

License

MIT

Why we included this project

Whisper Playground gives you a working web app rather than a script: a faster-whisper Python backend feeding a React frontend, with near real-time transcription in 99 languages. The Diart and Pyannote integration adds speaker diarization, so transcripts show who said what during a conversation instead of a single wall of text. Model size, beam size, and transcription timeout are exposed as config, letting you tune latency against accuracy for whatever hardware you have. With setup instructions and an online demo, it's a solid reference for teams prototyping meeting notes, live captioning, or call analysis.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category