feat(stage-ui): add GPT-SoVITS speech provider support#1577
feat(stage-ui): add GPT-SoVITS speech provider support#1577orangeZSCB wants to merge 3 commits intomoeru-ai:mainfrom
Conversation
## Summary - add GPT-SoVITS as a configurable speech provider in AIRI settings - add provider-specific settings UI and i18n entries for base URL, reference audio, prompt language, text language, and model weight switching - add Electron-side fetch proxy so remote GPT-SoVITS health checks and speech generation work in desktop without renderer CORS failures ## Notes - GPT-SoVITS integration targets api_v2.py style endpoints (api_v2.py provided by GPT-SoVITS original repo) - health check validates service availability through /set_gpt_weights - model switching is handled through GPT/SoVITS weight path endpoints instead of standard model selection ## Validation - pnpm typecheck ✅ - pnpm lint ❌ (repository has pre-existing unrelated lint errors outside this change set)
|
oh hell that i didnt notice some project can convert GPT-SoVITS to OpenAI format or something, but me did this feature, feeling that im a dumb |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c065fe6921
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
There was a problem hiding this comment.
Code Review
This pull request introduces the gpt-sovits speech provider, featuring a new configuration UI and store integration. It also adds an Electron-based fetch service to facilitate IPC-driven network requests for binary data. The review feedback points out a bug in header handling for Headers instances and requests the removal of several debug console.log statements within the provider validation functions.
|
f why there is so many ai |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a89a8d3bce
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| @@ -1 +0,0 @@ | |||
| sha256-69tCpJaxRUnyR9CrHlmWJWEWLDpYzyzska7ui9++QoY= | |||
There was a problem hiding this comment.
Restore non-empty Nix asset hash
This change clears nix/assets-hash.txt, but the Nix package definition reads this file as outputHash (checked in nix/common.nix). outputHash must be a valid SRI hash, so an empty string causes Nix builds/evaluation for this derivation to fail, breaking packaging/release flows that use the Nix build path.
Useful? React with 👍 / 👎.
| if (!config.baseUrl) { | ||
| return { errors: [new Error('Base URL is required')], reason: 'Base URL is required', valid: false } | ||
| } |
There was a problem hiding this comment.
Require GPT-SoVITS refAudioPath during validation
The GPT-SoVITS validator only gates on baseUrl, so this provider can be marked configured even when refAudioPath is missing. In the same provider implementation, the TTS request always sends ref_audio_path from config (defaulting to an empty string), which means runtime synthesis can fail immediately despite passing configuration checks. This should be validated up front to avoid false-positive readiness.
Useful? React with 👍 / 👎.
Summary
feat(stage-ui): add GPT-SoVITS speech provider support
Description
Notes
Validation
Linked Issues
#532 #1360