voicebox

mirror of https://github.com/jamiepine/voicebox.git synced 2026-09-15 12:50:42 -07:00

Files

T

James Pine ca74c155e2 fix: pass language parameter to Qwen TTS models and sync form with profile language

Both PyTorch and MLX backends silently dropped the language parameter —
it was accepted by generate() but never forwarded to the underlying
Qwen3-TTS model, causing it to default to auto-detection which
frequently confuses similar languages (e.g. Portuguese for Spanish).

- Add LANGUAGE_CODE_TO_NAME mapping (ISO 639-1 to full name) to both backends
- PyTorch: pass language= to generate_voice_clone()
- MLX: pass lang_code= to all 4 model.generate() call sites
- Frontend: auto-sync generation form language with selected voice profile

Closes #97

2026-03-13 04:04:04 -07:00

src

fix: pass language parameter to Qwen TTS models and sync form with profile language

2026-03-13 04:04:04 -07:00

components.json

Initialize voicebox project with backend, frontend, and Tauri setup. Added configuration files, dependencies, and basic structure for components, hooks, and utilities. Included README and setup documentation for guidance.

2026-01-25 02:19:06 -08:00

index.html

Update dependencies and enhance project structure. Upgraded Tailwind CSS to version 4.1.0, removed obsolete configuration files, and added a comprehensive CURRENT_STATE.md file detailing project features, architecture, and future plans. Improved history management in the backend with new response models and optimized API endpoints for better data handling.

2026-01-25 02:54:31 -08:00

package.json

Bump version: 0.1.12 → 0.1.13