Skip to content

Feat/voice provider registry#29

Open
achetronic wants to merge 2 commits intomasterfrom
feat/voice-provider-registry
Open

Feat/voice provider registry#29
achetronic wants to merge 2 commits intomasterfrom
feat/voice-provider-registry

Conversation

@achetronic
Copy link
Copy Markdown
Owner

TBD

Plan for multi-backend TTS/STT support. Extracts current OpenAI-only
proxy into a provider interface pattern (same as clients/memory
registries). First new provider: Gemini via generateContent API.
Designed for easy extensibility to xAI and future providers.

🐨 Generated with Crush

Assisted-by: Claude Opus 4.6 via Crush <crush@charm.land>
@achetronic achetronic self-assigned this Apr 9, 2026
@achetronic achetronic added the enhancement New feature or request label Apr 9, 2026
@achetronic achetronic force-pushed the feat/voice-provider-registry branch 18 times, most recently from c95f3b7 to 721f1e6 Compare April 10, 2026 12:59
Extract hardcoded OpenAI TTS/STT proxy into a provider interface
pattern matching the existing clients and memory registries. Add Gemini
provider that translates to generateContent API with speechConfig (TTS)
and inlineData (STT). TTSRef and BackendRef gain a Config map for
provider-specific extras. Admin API exposes GET /voice/types with JSON
Schemas. Frontend renders dynamic config fields per backend type.

Gemini TTS extras: languageCode, temperature, stylePrompt.
Gemini STT extras: transcriptionPrompt.

🐨 Generated with Crush

Assisted-by: Claude Opus 4.6 via Crush <crush@charm.land>
@achetronic achetronic force-pushed the feat/voice-provider-registry branch from 721f1e6 to 7ed5b27 Compare April 10, 2026 14:22
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant