Skip to content

Navigation Menu

Sign in
Sign up

Add MiniMax speech TTS to the Media Center extension - #232

Open
octo-patch wants to merge 3 commits into
Devin-AXIS:main from
octo-patch:octo/20260804-tts-tool-recvrehj3sXpPX
Open

Add MiniMax speech TTS to the Media Center extension #232
octo-patch wants to merge 3 commits into
Devin-AXIS:main from
octo-patch:octo/20260804-tts-tool-recvrehj3sXpPX

Conversation

@octo-patch

@octo-patch octo-patch commented Aug 4, 2026

Copy link
Copy Markdown
Contributor

Reason: Add MiniMax speech TTS to the Media Center extension.

Changes:

  • Add an optional minimax provider to the media speech_synthesize action; the default provider behavior is unchanged.
  • Call the MiniMax Text to Audio v2 endpoint for the global and China regional endpoints with model, text, voice_setting, audio_setting, pronunciation_dict, and output_format request fields.
  • Validate MiniMax responses through base_resp.status_code and expose data.audio / data.status in the action output.
  • Register MINIMAX_API_KEY as a Media authorization service so the key stays server-side.

Checks:

  • bun test apps/server/src/extensions/media-center.test.ts
  • bun test apps/server/src/extensions/storage.test.ts apps/server/src/extensions/media-center.test.ts
  • bun build apps/server/src/extensions/media-center.ts

Add an optional minimax provider to the media speech_synthesize action. It
calls the MiniMax Text to Audio v2 endpoint for the global and China regions,
sends voice_setting, audio_setting, pronunciation_dict, and output_format
request fields, and validates base_resp.status_code in the response.
Co-Authored-By: Claude <noreply@anthropic.com>

Copy link
Copy Markdown
Owner

Hi! Thanks so much for your continued support and for contributing this PR to the project.

We really appreciate the work you've put into improving the Media Center. We're also actively planning to expand our TTS capabilities and related media extensions, so your contribution is very timely.

We'd love to explore a deeper collaboration and discuss ideas around the future roadmap. If you're interested, feel free to reach out to me at [devin@ipollo.ai](mailto:devin@ipollo.ai). It would be great to connect and see how we can work together.

Thanks again for your support and contribution—we're looking forward to chatting with you!

Copy link
Copy Markdown
Contributor Author

Thanks for the context. I updated the MiniMax speech TTS adapter, resolved the latest main-branch conflict, and added request and response validation coverage. I ran the Media Center test file (41 tests) and the server typecheck.

Devin-AXIS requested review from DevJackKong and removed request for DevJackKong August 19, 2026 07:51

Copy link
Copy Markdown
Contributor Author

Thanks for the context. I resolved the current main-branch conflicts and updated the MiniMax credential lookup to the current Authorization Center interface, then pushed a new commit. I ran the Media Center test file (45 tests) and the server typecheck.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

AltStyle によって変換されたページ (->オリジナル) /