Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: give rustbot a voice #7

Merged
merged 5 commits into from
Apr 23, 2024
Merged

feat: give rustbot a voice #7

merged 5 commits into from
Apr 23, 2024

Conversation

milosgajdos
Copy link
Owner

@milosgajdos milosgajdos commented Apr 17, 2024

We introduce tts module that handles TTS tasks in rustbot. We use the playht_rs crate for TTS synthesis.
We had to revamp some things around such as the LLM having to send the chunks to both TTS and the jet.Reader.

We're using rodio crate for playing the bot speech.

We introduce a tts module that handles TTS tasks
of rustbot. We had to revamp some thing around such as the llm having to
send the chunks to both to TTS and the jet.Reader.
We're using rodio for playing the speech.

Signed-off-by: Milos Gajdos <[email protected]>
Previoously we would publish to jetstream as soon as
write_stream in TTS task completes. The issue with that is that since we
are playing audio in an async task, we never wait for the actual
audio to finish. We try to do that here. We also handle
audio player exit better here.

Signed-off-by: Milos Gajdos <[email protected]>
@milosgajdos milosgajdos merged commit 77ce5c0 into main Apr 23, 2024
5 checks passed
@milosgajdos milosgajdos deleted the rustbot-speak branch April 23, 2024 15:33
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant