{"data":{"slug":"debpalash-omnivoice-studio","name":"OmniVoice-Studio","tagline":"The open-source ElevenLabs alternative for local voice cloning and related tasks","github_url":"https://github.com/debpalash/OmniVoice-Studio","owner":"debpalash","repo":"OmniVoice-Studio","owner_avatar_url":"https://avatars.githubusercontent.com/u/4178343?v=4","primary_language":"Python","stars":33281,"forks":3929,"topics":["ai","audiobook","cuda","dubbing","elevenlabs-alternative","huggingface","local-first","mlx","omnivoice-studio","speech-to-text","tauri","text-to-speech","transcription","translate","tts","voice-ai","voice-cloning","voice-generation","voicestudio","workflow"],"archived":false,"github_pushed_at":"2026-09-20T05:11:11+00:00","maintenance_label":"Very active","stars_delta_30d":24072,"url":"https://www.graphcanon.com/tools/debpalash-omnivoice-studio","markdown_url":"https://www.graphcanon.com/tools/debpalash-omnivoice-studio.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/debpalash-omnivoice-studio","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=debpalash-omnivoice-studio","description":"VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.","homepage_url":"https://voicestudio.sh","license":"Other","open_issues":32,"watchers":131,"ai_summary":"OmniVoice Studio is an open-source app that allows users to design, create, dub, and dictate using text-to-speech technology on their local machine.","readme_excerpt":"### Install with prompt\n\nCopy this prompt into your coding agent to install VoiceStudio and configure it for your device:\n\n```text\nInstall and configure the VoiceStudio Electron desktop app on this device,\nthen verify it works. Tauri is archived; do not install or launch it.\nRepository: https://github.com/debpalash/VoiceStudio\n\nRead the repository's install guide for my OS, docs/performance.md, and\nskills/voicestudio/SKILL.md. Install the voicestudio audio-workflow skill\nwith `npx skills add debpalash/VoiceStudio` if your agent supports skills;\notherwise follow that SKILL.md directly.\n\nDetect my OS, CPU architecture, GPU, available RAM/VRAM, free disk space,\nand any existing VoiceStudio installation, backend, or downloaded models.\nReuse existing data and models. Prefer the latest stable Electron installer\nfor my OS and architecture; select an asset named VoiceStudio-Electron.\nFor source setup, follow electron/README.md: bun install, then bun run dev\nfrom the repository root. Let Electron supervise the backend; do not start\na second backend or use legacy tauri scripts.\nIf migrating from Tauri, follow docs/electron-migration.md and back up first.\n\nConfigure local voice cloning using a supported engine and acceleration\nthat fit this device. Keep working defaults and verify the actual execution\ndevice rather than assuming GPU support. Install required dependencies;\nreuse a suitable installed model, or explain the download size and license\nand ask before downloading one. Keep cloud services and analytics opt-in.\n\nStart the app, check /health at the configured backend address (default\nhttp://localhost:3900), and discover its API through /openapi.json. Generate\na short test with a bundled or authorized voice and verify the audio file.\nReport the installed version, engine, actual device, data location, audio\noutput path, and how to reopen the app. Complete the setup, not just a plan;\nidentify any permissions or manual steps you cannot perform.\n```\n\n<details>\n<summary><strong>Run the Electron preview from source</strong></summary>\n\n```bash\ngit clone https://github.com/debpalash/VoiceStudio.git\ncd VoiceStudio\nbun install\nbun run dev\n```\n\nSee [Electron setup](electron/README.md) for prerequisites and backend configuration.\n\nUse `bun run smoke-test` to build and launch an isolated packaged Electron app.\nAdd `-- --install` for the networked managed-runtime installation check.\n\n</details>\n\n> **Electron is the only maintained desktop app.** Version 0.5.3 was the final Tauri release. Existing Tauri users must [install Electron separately](docs/electron-migration.md). Root development, build, test, and release commands target Electron; Tauri source is archived and receives no further updates.\n\n---\n\n## License & responsible use\n\n[AGPL-3.0](LICENSE). Models have their own licenses; review them before commercial use. Clone voices only with permission. See [license details](LICENSE-NOTICE.md).","github_created_at":"2026-04-09T21:40:26+00:00","created_at":"2026-07-11T12:05:39.863203+00:00","updated_at":"2026-09-20T07:04:47.817343+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"asr","name":"asr"},{"slug":"dubbing-ai","name":"dubbing-ai"},{"slug":"local-ai","name":"local-ai"},{"slug":"speech-recognition","name":"speech recognition"},{"slug":"speech-to-text","name":"speech-to-text"},{"slug":"text-to-speech","name":"text-to-speech"},{"slug":"transcription","name":"transcription"},{"slug":"tts","name":"tts"}],"trust":{"provenance":{"is_fork":false,"github_id":1206390571,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T07:04:45.094Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":22,"days_since_push":0,"last_release_at":"2026-09-17T06:17:08Z","stars_delta_30d":24072,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:05:44.598Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T07:04:46.316Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T07:04:46.316Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-09-20T07:04:46.316Z"},"languages":{"value":["python","javascript","typescript"],"source":"github.language+package.json+pyproject.toml","observed_at":"2026-09-20T07:04:46.316Z"},"license_spdx":{"value":"AGPL-3.0","source":"github.license","observed_at":"2026-09-20T07:04:46.316Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["If you need a flexible solution that supports various operating systems including Apple Silicon and Linux with ROCm support for AMD GPUs under specific conditions.","For scenarios where running text-to-speech tasks locally is crucial due to bandwidth limitations or data privacy concerns."],"when_not_to_use":["Avoid if you are on an Intel-based macOS system, as the Python backend no longer supports this architecture and can only point to a remote backend.","Do not use if your GPU has less than 8 GB of VRAM and performance is critical -- TTS tasks will be offloaded onto the CPU, which may slow down operations."],"source":"enrich:decision_facts","observed_at":"2026-07-16T23:11:45.620Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"OmniVoice Studio is an open-source local voice cloning and text-to-speech app designed for users looking to create, dub, and dictate audio content on their own machines."}]}}