search

rhasspy / piper

A fast, local neural text to speech system
https://rhasspy.github.io/piper-samples/
MIT License
6.01k stars 437 forks source link

can this do speech to text too? #334

Closed ralyodio closed 9 months ago

ralyodio commented 9 months ago

I got the text to speech working, but I need the other direction now.

synesthesiam commented 9 months ago

No, Piper is text to speech only. You may want to check out whisper.

ralyodio commented 9 months ago

is there anythijng open source besides whisper which I assume requires payment for access to openai.com's api?

rmcpantoja commented 9 months ago

is there anythijng open source besides whisper which I assume requires payment for access to openai.com's api?

Hi @ralyodio, Whisper is an open-sourced model. The model in the API is the same but only hosted for online usage.

synesthesiam commented 9 months ago

Vosk and Coqui STT are two other open source systems. Vosk is based on Kaldi, which can be used directly too.