How no-needs/voicestudio works
VoiceStudio is a local-first AI voice studio for cloning and designing voices, generating speech, dubbing video, dictation/transcription, and narration. A typical workflow starts in the desktop workspace, uses backend APIs to configure engines or submit media and text, and returns generated or processed audio/video. The backend also exposes model setup, cloud sync, and telephony capabilities. The graph emphasizes documented backend call relationships; several UI-to-API connections are unverified because the excerpts do not show their transport wiring.
Main entry points: dub_core.py Dubbing API · engines.py Engine API · main.py API application · dub_pipeline.py Dubbing pipeline
Components 20
Desktop experience
- Studio workspace
electron/src/renderer/src/app.tsx
Backend API
- API application
backend/main.py - Dubbing API
backend/api/routers/dub_core.py - Engine API
backend/api/routers/engines.py - Model setup API
backend/api/routers/setup/models.py
Speech and media
- Dubbing pipeline
backend/services/dub_pipeline.py - Speech backends
backend/services/tts_backend.py - Transcription
backend/services/asr_backend.py - Media processing
backend/services/ffmpeg_utils.py
Runtime and state
- Model runtime
backend/services/model_manager.py - Device capabilities
backend/core/device_caps.py - App configuration
backend/core/config.py - User preferences
backend/core/prefs.py - Background tasks
backend/core/tasks.py - Job event store
backend/core/job_store.py - Failure reporting
backend/core/failure.py
Additional capabilities
- Cloud sync
backend/services/cloud_sync/engine.py - Dictation
backend/services/sherpa_dictation.py - Telephony
backend/services/telephony/agent.py
Other components
- Studio user
Connections 16
- Studio user → Studio workspace: uses
- Studio workspace → API application: requests
- API application → Background tasks: registers tasks
backend/main.py - API application → App configuration: configures
backend/main.py - Dubbing API → Dubbing pipeline: delegates to
backend/api/routers/dub_core.py - Dubbing API → Model runtime: uses
backend/api/routers/dub_core.py - Dubbing API → Transcription: transcribes with
backend/api/routers/dub_core.py - Dubbing pipeline → Model runtime: uses
backend/services/dub_pipeline.py - Dubbing pipeline → Media processing: processes media
backend/services/dub_pipeline.py - Engine API → Speech backends: lists backends
backend/api/routers/engines.py - Engine API → Transcription: lists backends
backend/api/routers/engines.py - Engine API → User preferences: reads choices
backend/api/routers/engines.py - Model setup API → Speech backends: checks backends
backend/api/routers/setup/models.py - Model runtime → Device capabilities: routes by device
backend/services/model_manager.py - Background tasks → Job event store: persists events
backend/core/tasks.py - Background tasks → Failure reporting: formats failures
backend/core/tasks.py