feat: add MiniMax TTS provider support#72
Open
octo-patch wants to merge 1 commit intogyoridavid:mainfrom
Open
Conversation
- Add MiniMaxVoiceEnum with 6 English voice options - Add MiniMax TTS library class with fetch-based API integration (non-streaming) - Update ShortCreator to auto-route to MiniMax TTS when a MiniMax voice is selected - MiniMax voices appear in /api/voices endpoint alongside Kokoro voices - Add MINIMAX_API_KEY environment variable support (optional, Kokoro remains default) - Add unit and E2E tests for the MiniMax TTS library
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR adds MiniMax as an optional cloud TTS provider alongside the existing local Kokoro TTS engine.
MiniMaxVoiceEnumwith 6 English voice options (English_Graceful_Lady,English_Insightful_Speaker,English_radiant_girl,English_Persuasive_Man,English_Lucky_Robot,English_expressive_narrator)src/short-creator/libraries/MiniMax.ts— a fetch-based MiniMax TTS client using the MiniMax T2A v2 APIShortCreatorto auto-route TTS calls: when aMiniMaxVoiceEnumvoice is selected, use MiniMax TTS; otherwise fall back to Kokoro (default unchanged)GET /api/voicesendpoint alongside Kokoro voicesMINIMAX_API_KEYenvironment variable support (optional — Kokoro remains the default, no breaking changes)Usage
Set
MINIMAX_API_KEYin your.envfile, then pass anyMiniMaxVoiceEnumvalue as thevoicefield when creating a video:{ "scenes": [{ "text": "Hello world!", "searchTerms": ["nature"] }], "config": { "voice": "English_Graceful_Lady" } }Kokoro remains the default when
voiceis unset or aVoiceEnumvalue is used.API Reference