Convert your speech to text using browser or extras.
  • JavaScript 100%
Find a file
2025-12-20 18:26:39 +02:00
browser.js Turn off the mic when switching providers 2024-07-12 20:30:31 +09:00
chutes.js Add ElevenLabs provider and update STT providers to include secret key handling 2025-12-20 18:26:39 +02:00
elevenlabs.js Add ElevenLabs provider and update STT providers to include secret key handling 2025-12-20 18:26:39 +02:00
groq.js Add ElevenLabs provider and update STT providers to include secret key handling 2025-12-20 18:26:39 +02:00
index.js Add ElevenLabs provider and update STT providers to include secret key handling 2025-12-20 18:26:39 +02:00
koboldcpp.js Add ZAI provider + refactor 2025-12-12 00:53:35 +02:00
LICENSE Initial commit 2023-10-13 01:11:20 +02:00
manifest.json Update manifest.json 2023-10-15 16:41:50 +03:00
mistral.js Add ElevenLabs provider and update STT providers to include secret key handling 2025-12-20 18:26:39 +02:00
README.md Update README and STT provider classes to enhance documentation and add provider notes 2025-12-13 17:53:26 +02:00
streaming.js Replace whitespace 2024-08-22 20:18:01 +03:00
stt-base.js Add ElevenLabs provider and update STT providers to include secret key handling 2025-12-20 18:26:39 +02:00
style.css Add extensions files with updated path for third-party folder. 2023-10-13 01:20:23 +02:00
vad.js Add voice activation and long push-to-talk 2024-06-05 01:01:01 +03:00
vosk.js Apply ESLint 2023-12-02 22:11:07 +02:00
wave-worker.js Add local whisper. Force convert recorded audio to WAV 2024-02-02 00:37:48 +02:00
whisper-extras.js Apply ESLint 2023-12-02 22:11:07 +02:00
whisper-local.js fix lang 2024-07-10 01:02:34 +09:00
whisper-openai.js Add ElevenLabs provider and update STT providers to include secret key handling 2025-12-20 18:26:39 +02:00
zai.js Add ElevenLabs provider and update STT providers to include secret key handling 2025-12-20 18:26:39 +02:00

Extension-Speech-Recognition

Convert your speech to text using one of the supported sources.

  • Browser (Web Speech API)
  • Whisper (OpenAI API)
  • Voxtral (MistralAI API)
  • GLM ASR (Z.AI API)
  • KoboldCpp
  • Groq
  • Chutes
  • and others...

Documentation: https://docs.sillytavern.app/extensions/speech-recognition/

License and credits

GPLv3

vad.js by kdavis-mozilla is from https://github.com/kdavis-mozilla/vad.js (BSD-3-Clause).