feat: Add Text-to-Speech #2012
Merged
feat: Add Text-to-Speech #2012
Conversation
This file contains hidden or 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
sestinj
requested changes
Aug 15, 2024
There was a problem hiding this comment.
@mkummer225 this is so cool! Small comments, let me know what you think. Very glad to see that you designed this so that it's open for extensibility with other providers
|
@sestinj thanks! Yup just incorporated those changes – definitely wanted to get a quick solution out (+wade in gently with my first PR) while giving any future TTS a home Pretty cool (& fast) CPU based model I came across while working this: |
This comment was marked as duplicate.
This comment was marked as duplicate.
Sorry, something went wrong.
sestinj
approved these changes
Aug 23, 2024
|
Congrats on PR number 1! |
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Outdated suggestions cannot be applied.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.
Description
This PR adds text-to-speech functionality using built-in, system TTS programs ("say ...", "espeak ...", etc).
It can be enabled via
experimental.readResponseTTSin continue's config.jsonTTS should work for OSX, Windows, and linux where
espeakis available – this PR still needs testing on Windows and Linux to confirm their implementations.When enabled, TTS will start after the full chat has been streamed. It will skip reading code blocks and only read the top level text response. When initiating a new chat it will automatically stop any current TTS. Additionally, there's a button added to the bottom of the sidebar (shown below) to manually stop TTS.
Checklist
dev, rather thanmainScreenshots
A
Stop TTSbutton has been added to the bottom of the sidebar while TTS is active. Clicking the button will stop the current TTSTesting
Pull and debug this branch then set
experimental.readResponseTTStotruein your config. Initiate a new chat with an LLM and after receiving the full response it should start reading aloud using your system's TTS capabilities.