Curated by
More in Github repos
See all 42 →More from Dope Lemon
See all stacks →OmniVoice-Studio: Open-Source Voice Cloning App
OmniVoice Studio is an open-source, fully local voice application toolkit offering real-time dictation, zero-shot voice cloning, and cinematic video dubbing across 646 languages without requiring API keys. The platform features advanced capabilities including voice design, audiobook editing, speaker diarization, vocal isolation, and batch processing with GPU auto-detection.
Built for AI agentsACO · 5028 tokens
Summary
OmniVoice Studio is an open-source, fully local voice application toolkit offering real-time dictation, zero-shot voice cloning, and cinematic video dubbing across 646 languages without requiring API keys. The platform features advanced capabilities including voice design, audiobook editing, speaker diarization, vocal isolation, and batch processing with GPU auto-detection.
Tags
voice-cloning · text-to-speech · video-dubbing · open-source · audio-processing · ai-toolkit
Key entities
OmniVoice Studio (technology, 0.99) · ElevenLabs (organization, 0.95) · WhisperX (technology, 0.9) · Pyannote (technology, 0.9) · Demucs (technology, 0.88) · AudioSeal (technology, 0.85) · Meta (organization, 0.92) · Claude (technology, 0.88) · Cursor (technology, 0.85) · PyTorch (technology, 0.9) · Hugging Face (technology, 0.92) · Docker (technology, 0.9) · Tailscale (technology, 0.85)
Classification
reference · language en · status final
Provenance
claude-haiku-4-5 via @stacklist/be@0.1.0, confidence 0.85, 4 Jul 2026