Add Fish Audio TTS service #899
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Closed
markbackman
force-pushed
the
mb/add-fish-audio
branch
from
f319d55 to
627c91f
Compare
aconchillo
approved these changes
Dec 22, 2024
|
LGTM! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Please describe the changes in your PR. If it is addressing an issue, please reference that as well.
I see one blocker. Frequently, I don't receive audio for the last message requested. Instead, it comes as the first audio message for the next text I push. I've tried flushing by pushing a stop message after pushing the text to the websocket, but that doesn't seem to do the trick. Other than that, this is working well.
This is easy to repro, by running the example I've shared. I'll reach out to the Fish support team.
UPDATE (12/21/24):
I got a response from the Fish support team. They shared that they have a flush message that can be sent to force the model to generate and send the audio. This resolved the issue. This is now ready for review!