{"full_name":"jamiepine/voicebox","owner":"jamiepine","name":"voicebox","url":"https://github.com/jamiepine/voicebox","description":"The open-source AI voice studio. Clone, dictate, create.","homepage":"https://voicebox.sh","topics":[],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/32987599?u=38da1b8ee28b42a8509516607a1b74bb22b13402&v=4","created_at":"2026-01-25T12:27:03Z","pushed_at":"2026-10-07T01:17:58Z","metrics":{"stars":60340,"forks":7579,"watchers":263,"issues":756,"prs":465,"releases":25,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":0},"growth":{"day":{"stars":136,"forks":11,"base_day":"2026-11-09"},"week":{"stars":1063,"forks":150,"base_day":"2026-11-03"},"month":{"stars":4090,"forks":573,"base_day":"2026-10-11"}},"history":{"dates":["2026-09-06","2026-09-07","2026-09-08","2026-09-09","2026-09-10","2026-09-11","2026-09-12","2026-09-13","2026-09-14","2026-09-15","2026-09-16","2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-09","2026-11-10"],"stars":[51124,51326,51445,51530,51629,51671,51709,51788,52045,52154,52234,52317,52373,52506,52659,52797,52908,53001,53051,53232,53834,54247,54753,55098,55174,55368,55453,55527,55585,55682,55764,55914,55991,56108,56143,56250,56429,56497,56578,56657,56740,56800,57090,57348,57461,57704,57842,58014,58089,58175,58242,58386,58451,58617,58728,58885,58987,59064,59277,59350,60204,60340],"forks":[6376,6406,6418,6426,6437,6439,6441,6448,6482,6495,6504,6517,6527,6547,6567,6585,6603,6622,6630,6648,6733,6782,6814,6857,6880,6906,6918,6924,6928,6937,6947,6966,6977,7005,6994,7006,7031,7039,7048,7064,7073,7079,7116,7167,7194,7228,7251,7274,7287,7304,7310,7326,7333,7364,7380,7403,7407,7414,7429,7440,7568,7579],"watchers":[234,234,236,236,235,236,237,239,242,242,242,242,242,243,245,246,244,244,245,247,250,252,257,259,260,260,260,259,260,259,260,260,260,259,261,259,255,255,251,253,254,254,255,255,256,257,258,258,260,263,263,263,259,260,260,261,262,261,260,260,263,263],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null]},"boards":{"weekly":117,"monthly":132,"monthly_rate":180},"same_owner":[],"issues":[{"number":185,"title":"Fine Tune Instructions","comments":32,"created_at":"2026-02-24T14:23:51Z"},{"number":98,"title":"Connecting to Download..","comments":16,"created_at":"2026-02-18T22:15:59Z"},{"number":513,"title":"\"Server startup failed Server process ended unexpectedly\"","comments":15,"created_at":"2026-04-20T14:26:44Z"},{"number":20,"title":"Model download failed","comments":13,"created_at":"2026-01-30T21:05:41Z"},{"number":676,"title":"DirectML backend support for Windows AMD/Intel GPUs","comments":9,"created_at":"2026-05-18T18:57:26Z"},{"number":452,"title":"ERROR LOAD MODEL","comments":8,"created_at":"2026-04-17T08:26:17Z"},{"number":74,"title":"Errno 22 Invalid argument","comments":8,"created_at":"2026-02-16T13:56:50Z"},{"number":42,"title":"American accent even with Scottish voice","comments":8,"created_at":"2026-02-02T15:54:14Z"}],"discussions":[],"latest_release":{"name":"v0.5.0","tag":"v0.5.0","published_at":"2026-04-25T22:46:53Z","body":"## The Capture release.\r\n\r\nVoicebox stops being just a voice-cloning studio and becomes a full AI voice studio. Hold a key anywhere on your machine, speak, release — the transcript lands in the focused text field. Flip the primitive around and any MCP-aware agent — Claude Code, Cursor, Spacebot — speaks back through an on-screen pill in one of your cloned voices. A local LLM sits between the two, so transcripts come out clean and voice profiles can carry a personality that reshapes what the agent says before it gets spoken.\r\n\r\n<img width=\"1354\" height=\"990\" alt=\"Screenshot 2026-04-22 at 2 37 10 PM\" src=\"https://github.com/user-attachments/assets/853c730f-64f3-4573-bcd8-1000bdb8e11f\" />\r\n\r\n### Dictation — speak anywhere, paste anywhere\r\n\r\n- **Global hotkey capture.** Hold a customizable chord anywhere on your machine (defaults: right-Cmd + right-Option on macOS, right-Ctrl + right-Shift on Windows), speak, release. A floating on-screen pill walks through recording → transcribing → refining → done with a live elapsed timer. The transcript lands as clean text.\r\n- **Push-to-talk and toggle modes, each with its own chord.** The default toggle chord adds Space to the push-to-talk chord. Holding PTT and tapping Space mid-hold upgrades a hold into a hands-free session without a gap in the recording.\r\n- **Auto-paste into the focused app.** Once transcription finishes, Voicebox synthesizes a paste into whatever text field had focus when you started the chord — not wherever focus drifted while you were talking. Works across Dvorak / AZERTY layouts. Your clipboard is saved before and restored after.\r\n- **Chord picker UI.** Customize either chord from Settings → Captures by holding the keys you want. Left/right modifier badges show whether a key is the left or right variant.\r\n- **Defaults stay out of your way.** macOS defaults avoid left-hand Cmd+Option chords so the system shortcuts they collide with stay yours. Windows defaults route around AltGr collisions on German / French / Spanish layouts.\r\n- **Accessibility permission is scoped.** If macOS Accessibility isn't granted, dictation still runs and transcripts still land in the Captures tab — only synthetic paste is disabled. The permission prompt lives inline next to the auto-paste toggle, not as a global banner.\r\n\r\n### Personality — voice profiles that speak for themselves\r\n\r\nVoice profiles now carry an optional **personality** — a free-form description of who this voice is, up to 2000 characters. When set, two new controls appear next to the generate button, each powered by a new Qwen3 LLM running entirely locally:\r\n\r\n- **Compose** — the shuffle button drops a fresh in-character line into the textarea. Click again for variety, edit before speaking.\r\n- **Speak in character** — the wand toggle runs your input through the personality LLM before TTS, preserving every idea but delivering it in the character's voice.\r\n\r\nThe same LLM doubles as the refinement model, so there's one local LLM in the app, not two.\r\n\r\n**API surface.** `POST /generate`, `POST /speak`, and the MCP `voicebox.speak` tool accept `personality: bool`. `POST /profiles/{id}/compose` powers the shuffle button. MCP client bindings carry a `default_personality: bool` that applies when `personality` isn't passed explicitly.\r\n\r\n### Agents — any MCP-aware agent gets a voice\r\n\r\nVoicebox ships a built-in **Model Context Protocol** server at `http://127.0.0.1:17493/mcp` so Claude Code, Cursor, Windsurf, Cline, VS Code MCP extensions — any MCP-aware agent — can call into your local Voicebox install. Four tools ship with dotted names:\r\n\r\n- **`voicebox.speak`** — speak text in any voice profile, with optional `personality: true` to run through the profile's personality LLM first\r\n- **`voicebox.transcribe`** — Whisper transcription of a base64 blob or an absolute local path. Path mode is restricted to loopback callers so a Voicebox bound on `0.0.0.0` doesn't double as an unauthenticated arbitrary-local-file read primitive.\r\n- **`voic"},"readme":true,"readme_zh":false,"news":[{"title":"Open-source voice cloning app using Qwen3-TTS","url":"https://github.com/jamiepine/voicebox","hn":"https://news.ycombinator.com/item?id=47073053","source":"Hacker News","lang":"en","date":"2026-02-19","points":4,"comments":0},{"title":"Voicebox: The Open-Source AI Voice Studio","url":"https://github.com/jamiepine/voicebox","hn":"https://news.ycombinator.com/item?id=48863385","source":"Hacker News","lang":"en","date":"2026-07-10","points":1,"comments":0},{"title":"Voicebox – The open-source voice synthesis studio","url":"https://github.com/jamiepine/voicebox","hn":"https://news.ycombinator.com/item?id=47831411","source":"Hacker News","lang":"en","date":"2026-04-20","points":1,"comments":0},{"title":"Free OSS brings $22/month voice cloning to local machines. AI agents start speaking with 'your voice' via Voicebox","url":"https://note.com/panda_lab/n/ndb2b6aa58132?hl=en","source":"note","lang":"en","date":"2026-07-22"},{"title":"Privacy-Focused Voice Interaction Realized with the Locally-Complete AI Voice Studio \"Voicebox\"","url":"https://note.com/h3adeu/n/n8d608f6d8ada?hl=en","source":"note","lang":"en","date":"2026-07-08"},{"title":"2026年最好的声音克隆工具？Voicebox完整测评：从下载到API调用，附速度对比","url":"https://www.bilibili.com/video/BV1np9ZBwETa/","source":"bilibili","lang":"zh","date":"2026-05-02"},{"title":"Voicebox Clones Any Voice From 3 Seconds of Audio, Runs Locally for Free, and Has No Consent Lock","url":"https://news.google.com/rss/articles/CBMizwFBVV95cUxNTmNlZGRTd0hVanlHOU1oOVBYMWdKel9Qa2RHTmswRGpCb01kS2M3T3Zfd1FaUGhSSFBkbklhc3hqSUVEcVZwX09GS0d4OFU0M2xaMFhzZnJfWERuOWRfYkt4MmdEMDQ4WlFwUjgyUVFPdS1xZHN2Wjhicll0UVJHclQwN0drdnNVLXpjaHExNG1jUzZSNG5HNGNUNVFZWkRRX3pRT1JFM3ZLNmUxQVJsQ2ctRDZLX0htTWdMRHBwTnU5czhBM0gwaWN1eFBnVEE?oc=5","source":"Tech Times","lang":"en","date":"2026-05-19"},{"title":"I replaced ElevenLabs with this free, open-source voice cloner, and the quality is scarily good","url":"https://news.google.com/rss/articles/CBMijAFBVV95cUxOQklNWEF6MldfVTVkQnNRWklCcWlqUDM4SWk2YWRrQmlwbWU5S01ZTmZENXAxOFVhQ0xzcHlIeWdDdDdaTEF0WmxDRlpibFpfbG9KaGpvTTVhVmNXbktmNDlfZUtwUTJmblQ4UVhSXzZLcmdibGxVeFFmS3NjQ0VJZGRCNlNDZzNWS0Vkcw?oc=5","source":"How-To Geek","lang":"en","date":"2026-05-18"},{"title":"Meta Voicebox Uses Generative AI to Replicate Voices from Scratch in Six Languages","url":"https://news.google.com/rss/articles/CBMihgFBVV95cUxNb2JMS0s0dHY1TG1wZDN5YWhlb3hsa2pHbC1ITnZFUGF3a1Z5UDVWOEpEYW5MaDlUWXJHeTFpM2lWcGxtampGZkVKTTVlVVVKN2JCdmdYRWhhMVRfbnY3OG40SjRiRmZnTnpVWVlaRElRbXNGWnI1Vm53VGtnWVZpQ2VGanhBQQ?oc=5","source":"TechEBlog -","lang":"en","date":"2023-07-01"}],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}