Skip to content

feat(compute): add MiMo speech protocol metadata - #68

Draft
Johnson-LYS wants to merge 1 commit into
mainfrom
codex/asr-tts-model-metadata
Draft

feat(compute): add MiMo speech protocol metadata#68
Johnson-LYS wants to merge 1 commit into
mainfrom
codex/asr-tts-model-metadata

Conversation

@Johnson-LYS

Copy link
Copy Markdown
Contributor

Summary

  • add backward-compatible extra.modelOrigin and extra.speech model-spec metadata
  • describe MiMo V2.5 ASR/TTS protocol families independently from compute provider routing
  • add the direct MiMo ASR model and correct official V2.5 TTS voices/formats
  • bump presetDataVersion from 79 to 80

Compatibility

  • all new fields live under the existing open spec.extra extension point
  • existing model-spec documents without speech metadata remain valid
  • strict nested validation rejects malformed speech profiles without changing legacy provider schema

Verification

  • npm run validate (74 validated, 0 failed)
  • npm test (45 passed)
  • DesireCore targeted speech compatibility/provider/resolver tests (19 passed)

Official sources

Rollout

Draft for isolated DesireCore developer-ref E2E. Do not merge or sync the client bootstrap zip until the runtime integration is verified.

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant