{"version":"v1","licence":"CC-BY-4.0","id":"voicebox","name":"Voicebox","repo":"jamiepine/voicebox","repository_url":"https://github.com/jamiepine/voicebox","docs_url":"https://docs.voicebox.sh","description":"Local desktop voice studio that clones voices, generates speech with 8 TTS engines, transcribes with Whisper and adds system-wide dictation.","summary":"Voicebox (v0.5.0 release April 2026, changelog to v0.6.0 in Oct 2026, ~59k stars, last commit 7 Oct 2026) is a Tauri desktop app with a Python backend that runs on your machine. It clones voices from a short sample, generates speech in 23 languages with engines such as Qwen3-TTS, Chatterbox and Kokoro, and has a multi-track Stories editor, audio effects, Whisper transcription, a dictation hotkey, a REST API and an MCP server so agents can speak in your voices. Installers for macOS and Windows, Docker, Linux from source. MIT.","capabilities":["speech-generation","voice-cloning","speech-recognition"],"tags":["Desktop app","Text-to-speech","Voice cloning","Speech-to-text","Dictation","Runs AI locally","Multilingual","MCP support","API","Docker"],"alternatives":[{"product":"elevenlabs","jobs":["speech-generation","voice-cloning","speech-recognition"],"coverage":"partial","note":"Covers local speech generation, voice cloning and Whisper transcription; no hosted conversational voice agent platform, only an MCP tool that lets coding agents speak."},{"product":"descript","jobs":["speech-generation","voice-cloning"],"coverage":"partial","note":"Voice cloning and text-to-speech with a multi-track timeline for audio; no transcript-based audio or video editing."}],"facts":{"runs_locally":{"status":"yes","value":"Runs entirely on your machine; an optional remote mode runs the backend on another machine such as a GPU server","source_url":"https://github.com/jamiepine/voicebox#what-is-voicebox","checked_at":"2026-10-29","confidence":"high","validation":"documentation_review","modes":["local","self-hosted"],"untrusted_source_quote":"models, voice data, and captures never leave your machine"},"code_license":{"status":"yes","value":"MIT","source_url":"https://github.com/jamiepine/voicebox/blob/main/LICENSE","checked_at":"2026-10-29","confidence":"high","validation":"documentation_review","spdx":"MIT","untrusted_source_quote":"MIT License"},"model_license":{"status":"partial","value":"Each TTS engine downloads its own weights under its own licence (Kokoro and Qwen3-TTS VoiceDesign are Apache-2.0); the opt-in OmniVoice engine has CC-BY-NC weights and is labelled non-commercial","source_url":"https://github.com/jamiepine/voicebox/blob/main/CHANGELOG.md","checked_at":"2026-10-29","confidence":"medium","validation":"documentation_review","spdx":null,"applies":true,"untrusted_source_quote":"The weights are CC-BY-NC, so the engine is labelled non-commercial in the engine picker and model manager and is never a default."},"commercial_use":{"status":"partial","value":"MIT code allows commercial use; output from the OmniVoice engine must not be used commercially, and other engines follow their own weight licences","source_url":"https://github.com/jamiepine/voicebox/blob/main/CHANGELOG.md","checked_at":"2026-10-29","confidence":"medium","validation":"documentation_review","untrusted_source_quote":"The weights are CC-BY-NC, so the engine is labelled non-commercial in the engine picker and model manager and is never a default."},"paid_services":{"status":"yes","value":"None; speech generation, transcription and the bundled Qwen3 LLM all run locally","source_url":"https://github.com/jamiepine/voicebox#what-is-voicebox","checked_at":"2026-10-29","confidence":"high","validation":"documentation_review","required":[],"optional":[],"untrusted_source_quote":"The full voice I/O stack, running locally on your machine."},"hardware":{"status":"yes","value":"Minimum 8 GB RAM, 5 GB free disk and a modern multi-core CPU; 16 GB+ RAM and a CUDA GPU recommended. Also uses Apple Silicon (MLX), ROCm, DirectML and Intel Arc","source_url":"https://github.com/jamiepine/voicebox/blob/main/docs/content/docs/overview/installation.mdx","checked_at":"2026-10-29","confidence":"high","validation":"documentation_review","cpu_ok":true,"min_vram_gb":null,"min_ram_gb":8,"untrusted_source_quote":"CPU inference is supported but significantly slower than GPU."},"platforms":{"status":"yes","value":"macOS 11+ (Apple Silicon and Intel) and Windows 10+ installers; Linux builds from source (no prebuilt binaries yet); Docker image","source_url":"https://github.com/jamiepine/voicebox#download","checked_at":"2026-10-29","confidence":"high","validation":"documentation_review","windows":"yes","macos":"yes","linux":"partial","untrusted_source_quote":"Pre-built binaries are not yet available."},"setup":{"status":"yes","value":"Easy on macOS and Windows; download the DMG or MSI and the first generation downloads its model (about 350 MB to 8 GB). Linux needs a source build","source_url":"https://github.com/jamiepine/voicebox/blob/main/docs/content/docs/overview/installation.mdx","checked_at":"2026-10-29","confidence":"high","validation":"documentation_review","level":"easy","untrusted_source_quote":"First generation will be slower due to model downloads."}},"metrics":{"stars":59296,"forks":7432,"contributors":106,"archived":false,"last_push_at":"2026-10-07T01:17:58Z","latest_release":{"tag":"v0.5.0","published_at":"2026-04-25T22:46:53Z"},"fetched_at":"2026-11-03T01:20:55.050Z"},"url":"https://repoquarry.dev/projects/voicebox","note":"Installation guidance: follow docs_url. This service never installs or runs code."}