-
|
I wanted to know if it'is possible to optimise latency generation. I don't know if there is an option to preload the speak_wav voice or embeddings ? |
Beta Was this translation helpful? Give feedback.
Answered by
eginhard
Feb 11, 2026
Replies: 1 comment
-
|
Yes, you can cache the embeddings for later use: https://coqui-tts.readthedocs.io/en/latest/cloning.html#usage Otherwise XTTS also supports streaming synthesis: https://coqui-tts.readthedocs.io/en/latest/models/xtts.html#streaming-manually |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
abentabib
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Yes, you can cache the embeddings for later use: https://coqui-tts.readthedocs.io/en/latest/cloning.html#usage
Otherwise XTTS also supports streaming synthesis: https://coqui-tts.readthedocs.io/en/latest/models/xtts.html#streaming-manually