{"full_name":"k2-fsa/OmniVoice","owner":"k2-fsa","name":"OmniVoice","shard":"1","url":"https://github.com/k2-fsa/OmniVoice","description":"High-Quality Voice Cloning TTS for 600+ Languages","homepage":"","topics":[],"tag_pages":[],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/71431748?v=4","created_at":"2026-03-31T12:00:45Z","pushed_at":"2026-11-09T22:30:45Z","metrics":{"stars":16613,"forks":2442,"watchers":72,"issues":219,"prs":80,"releases":6,"issues_open":49,"issues_closed":170,"prs_open":36,"prs_closed":15,"prs_merged":29,"discussions":0},"growth":{"day":{"stars":12,"forks":0,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[16457,16507,16537,16544,16575,16601,16613],"forks":[2415,2422,2432,2434,2441,2442,2442],"watchers":[null,71,71,71,71,71,72],"issues_open":[null,48,48,48,49,49,49],"prs_open":[null,34,35,35,35,36,36]},"boards":{},"same_owner":[{"full_name":"k2-fsa/sherpa-onnx","name":"sherpa-onnx","shard":"1","boards":{}}],"issues":[{"number":244,"title":"Clarifications on multilingual data construction (resampling, prompt-denoising, subset of data augmentation, restoration/filtering, text tokenizer) + request for implementation code","comments":18,"created_at":"2026-08-04T12:25:02Z"},{"number":129,"title":"Stress control","comments":11,"created_at":"2026-04-26T16:37:19Z"},{"number":82,"title":"谢谢，这个项目非常的不错，克隆声音也很好，使用起来也非常简单，赞👍 我写了个HTTP接口，大家可以看下","comments":11,"created_at":"2026-04-10T09:24:05Z"},{"number":258,"title":"Commercial use / commercial license for OmniVoice pretrained model","comments":10,"created_at":"2026-08-29T11:59:03Z"},{"number":235,"title":"Request for Commercial License – OmniVoice TTS for YouTube Content","comments":10,"created_at":"2026-07-24T05:03:30Z"},{"number":67,"title":"AMD GPU support","comments":10,"created_at":"2026-04-08T13:50:54Z"},{"number":237,"title":"Reducing Inconsistent Word Pronunciation Across Generations","comments":7,"created_at":"2026-07-28T03:29:02Z"},{"number":131,"title":"Community experiment: OmniVoice C++/GGML inference runtime","comments":7,"created_at":"2026-04-27T09:43:42Z"}],"discussions":[],"latest_release":{"name":"0.2.1","tag":"0.2.1","published_at":"2026-07-16T04:47:24Z","body":"## What's Changed\r\n* Add audio.cpp to community projects by @0xShug0 in https://github.com/k2-fsa/OmniVoice/pull/209\r\n* Make flex_attention honor autocast (fixes silent fp32 attention, ~4x training slowdown) by @shuaills in https://github.com/k2-fsa/OmniVoice/pull/212\r\n* Honor asr_model_name when the ASR model is loaded lazily by @HenryVarro666 in https://github.com/k2-fsa/OmniVoice/pull/221\r\n* Add VoiceClonePrompt.save()/load() for cross-session voice reuse by @HenryVarro666 in https://github.com/k2-fsa/OmniVoice/pull/223\r\n* Fix ASR model always loading on GPU 0; add asr_device option by @HenryVarro666 in https://github.com/k2-fsa/OmniVoice/pull/224\r\n* Avoid decoding the full reference audio just to get its duration by @aradix85 in https://github.com/k2-fsa/OmniVoice/pull/220\r\n* Add opt-in text normalization (numbers, dates, currency) via generate(normalize_text=True) by @HenryVarro666 in https://github.com/k2-fsa/OmniVoice/pull/227\r\n* Add stale issue workflow by @zhu-han in https://github.com/k2-fsa/OmniVoice/pull/228\r\n\r\n## New Contributors\r\n* @0xShug0 made their first contribution in https://github.com/k2-fsa/OmniVoice/pull/209\r\n* @shuaills made their first contribution in https://github.com/k2-fsa/OmniVoice/pull/212\r\n* @HenryVarro666 made their first contribution in https://github.com/k2-fsa/OmniVoice/pull/221\r\n* @aradix85 made their first contribution in https://github.com/k2-fsa/OmniVoice/pull/220\r\n\r\n**Full Changelog**: https://github.com/k2-fsa/OmniVoice/compare/0.2.0...0.2.1","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}