Piper and Whisper have risen to become a relatively popular set of apps to generate voice or to detect and recognize it. They use the Wyoming protocol to communicate with clients.
It would be great if the Open-WebUI administrator could connect users' conversations to Piper and Whisper, rather than having to load a second copy of the Whisper model for STT and having no local option for TTS.
Originally created by @Rudd-O on GitHub (Jan 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/9060
# Feature Request: Wyoming components for STT/TTS
Piper and Whisper have risen to become a relatively popular set of apps to generate voice or to detect and recognize it. They use the Wyoming protocol to communicate with clients.
It would be great if the Open-WebUI administrator could connect users' conversations to Piper and Whisper, rather than having to load a second copy of the Whisper model for STT and having no local option for TTS.
Context:
* https://github.com/rhasspy/wyoming-faster-whisper
* https://github.com/rhasspy/piper
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @Rudd-O on GitHub (Jan 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/9060
Feature Request: Wyoming components for STT/TTS
Piper and Whisper have risen to become a relatively popular set of apps to generate voice or to detect and recognize it. They use the Wyoming protocol to communicate with clients.
It would be great if the Open-WebUI administrator could connect users' conversations to Piper and Whisper, rather than having to load a second copy of the Whisper model for STT and having no local option for TTS.
Context:
@tjbck commented on GitHub (Jan 29, 2025):
They should be supported if they provide openai compatible endpoints!