docs: add OpenAI-compatible endpoint example to speech TTS config - #741
Open
AALG123 wants to merge 1 commit into
Open
docs: add OpenAI-compatible endpoint example to speech TTS config#741AALG123 wants to merge 1 commit into
AALG123 wants to merge 1 commit into
Conversation
|
@AALG123 is attempting to deploy a commit to the LibreChat's projects Team on Vercel. A member of the Team first needs to authorize it. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The
tts.openaioption table documentsurlas "Use for OpenAI-compatible endpoints", but the page has no example of what a working config looks like, so operators have to guess whetherurltakes a base URL or the full speech path.This adds one short subsection directly after the existing
openaiexample: a#### OpenAI-compatible endpointsnote plus one yaml block using Gandr as the concrete endpoint (https://tts.gandr.ai/v1/audio/speech). The values are real: the endpoint implementsPOST /v1/audio/speech, acceptstts-1as the model, maps the OpenAI voice names onto its own voices or takes its native voice ids, and returns mp3 by default, so LibreChat works with it unchanged. Nothing else on the page is touched.Happy to drop the vendor mention and rewrite it with a placeholder host if you prefer a neutral example.
Disclosure: I work on Gandr.