VoiceStudio
Clone voices, dub video, dictate, and produce long-form audio on your own hardware.
VoiceStudio (formerly OmniVoice-Studio) is a local-first voice AI platform that runs entirely on your own hardware. It integrates 16 TTS engines and 11 ASR engines, supports 646 languages, and offers voice cloning, video dubbing, dictation, story/audiobook production, and batch generation. No account, API key, subscription, or usage meter required for the local workflow. Available for macOS, Windows, Linux, and Docker, with CUDA, Apple Silicon MPS/MLX, ROCm, and CPU support.
Key Features
- Zero-shot voice cloning from 3-15 second reference clip
- 16 TTS engines with 646+ language catalogue
- 11 ASR engines for transcription and dictation
- Video dubbing with speaker preservation and translation
- System-wide dictation widget with live transcription
- Multi-voice story and audiobook production with .m4b export
- EPUB/PDF import for long-form audio generation
- Batch queue for large audio and video jobs
- OpenAI-compatible local audio API and MCP Server
- Vocal isolation and speaker diarization
- AI watermark embedding and detection (AudioSeal)
- Local-first: all data stays on your machine
- CUDA, Apple Silicon MPS/MLX, ROCm, and CPU support
- macOS, Windows, Linux, and Docker availability
Ratings & Reviews
Loading reviews…
Related Tools
Concat
The free, open-source CapCut replacement. Edit videos locally with no watermarks, no account, no subscriptions.
Concat is a free, open-source video editor that replaces CapCut without the watermarks, paywalls, or subscriptions. A native Rust engine handles the heavy lifting, a clean React interface provides the editing experience, and everything runs on your own machine. Features include multi-track editing with multiple timelines per project, split/trim/merge/transitions/speed control, auto-captions that run entirely locally (your audio never leaves your device), free local Text-to-Speech, voice filters, titles and styled text, and reusable templates. No watermarks, no account, nothing behind a paywall. Works on macOS, Windows, and Linux.
Stable Diffusion
Open-source image generation with full control — run locally or in the cloud, free to use.
Stable Diffusion is an open-source text-to-image model by Stability AI. Because it is open weight, it can run locally on your own GPU, be fine-tuned, and is the foundation of countless tools (AUTOMATIC1111, ComfyUI, Leonardo). It offers unmatched flexibility, negative prompts and community checkpoints.
ElevenLabs
Ultra-realistic AI voices for speech, dubbing and audio — clone, generate and localize.
ElevenLabs is the leading AI voice platform. It turns text into lifelike speech in 30+ languages, clones voices with a few minutes of audio, and offers AI dubbing for videos. It powers audiobooks, game characters, YouTube narration, agents and accessibility tools.