{"adoption": {"forks": 6004, "observed_at": "2026-08-28T04:12:18.017609+00:00", "stars": 53225}, "canonical_url": "https://ross.abutalabs.com/products/vibevoice", "card": {"archived": false, "artifact_type": "library", "description": "Open-Source Frontier Voice AI", "domain": ["speech-processing", "artificial-intelligence", "deep-learning"], "enriched": true, "function": ["tts", "speech-recognition", "machine-learning", "llm-inference"], "health_score": 76, "homepage": "https://microsoft.github.io/VibeVoice/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["microsoft/VibeVoice"], "name": "microsoft/VibeVoice", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-24T09:24:29+00:00", "repo": "microsoft/VibeVoice", "stars": 53225, "tags": ["text-to-speech", "speech-synthesis", "asr", "multi-speaker", "podcast-generation", "diffusion", "voice-ai", "long-form-audio", "audio", "gpu"], "topics": [], "urls": [], "use_cases": ["generate a multi-speaker podcast from a text script", "synthesize long-form conversational speech with consistent voices", "transcribe hour-long audio with speaker labels and timestamps", "convert text to expressive speech with emotion and singing", "cross-lingual speech generation between Mandarin and English", "run speech recognition on CPU at the edge", "finetune a TTS or ASR model on custom voice data"], "what_it_is": "VibeVoice is Microsoft's open-source frontier voice AI framework combining a next-token diffusion text-to-speech model for expressive, long-form, multi-speaker conversational audio (up to 90 minutes, 4 speakers) with VibeVoice-ASR, a unified speech-to-text model for hour-long transcriptions with speaker and timestamp annotations. It is distributed as Python models on Hugging Face and PyPI, with finetuning code and an edge CPU inference engine.", "when_to_avoid": ["you need a lightweight production TTS API with minimal compute", "you require strict guarantees against voice cloning misuse", "you need real-time low-latency streaming synthesis on modest hardware", "you only need simple single-phrase text-to-speech"], "when_to_choose": ["you need long-form multi-speaker speech synthesis beyond typical 1-2 speaker TTS limits", "you want open-source, MIT-licensed state-of-the-art TTS or ASR models", "you need structured transcriptions with speaker and timestamp metadata", "you want to finetune speech models on your own data"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/vibevoice", "repo": "microsoft/VibeVoice", "role": "main", "score": 60}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:19:34.204180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba850794c6d6a162f5eb1a801c147968034de0635e4cc665c6b16c4b56f1135b", "fetched_at": "2026-08-28T04:12:18.017609+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/VibeVoice"}, {"content_hash": "a784683f40081eb4874f60a8a447612fe875147f266d13337bb88ecc8b5f6934", "fetched_at": "2026-08-28T18:07:25.099994+00:00", "kind": "homepage", "missing": false, "url": "https://microsoft.github.io/VibeVoice/"}, {"content_hash": "b7b8a783e96d0df0421bb2d2751fb9ee14c25ac452d50432a96b48a83b521e81", "fetched_at": "2026-08-28T18:07:25.109002+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/vibevoice/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:19:34.204180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba850794c6d6a162f5eb1a801c147968034de0635e4cc665c6b16c4b56f1135b", "fetched_at": "2026-08-28T04:12:18.017609+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/VibeVoice"}, {"content_hash": "a784683f40081eb4874f60a8a447612fe875147f266d13337bb88ecc8b5f6934", "fetched_at": "2026-08-28T18:07:25.099994+00:00", "kind": "homepage", "missing": false, "url": "https://microsoft.github.io/VibeVoice/"}, {"content_hash": "b7b8a783e96d0df0421bb2d2751fb9ee14c25ac452d50432a96b48a83b521e81", "fetched_at": "2026-08-28T18:07:25.109002+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/vibevoice/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:19:34.204180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba850794c6d6a162f5eb1a801c147968034de0635e4cc665c6b16c4b56f1135b", "fetched_at": "2026-08-28T04:12:18.017609+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/VibeVoice"}, {"content_hash": "a784683f40081eb4874f60a8a447612fe875147f266d13337bb88ecc8b5f6934", "fetched_at": "2026-08-28T18:07:25.099994+00:00", "kind": "homepage", "missing": false, "url": "https://microsoft.github.io/VibeVoice/"}, {"content_hash": "b7b8a783e96d0df0421bb2d2751fb9ee14c25ac452d50432a96b48a83b521e81", "fetched_at": "2026-08-28T18:07:25.109002+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/vibevoice/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:19:34.204180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba850794c6d6a162f5eb1a801c147968034de0635e4cc665c6b16c4b56f1135b", "fetched_at": "2026-08-28T04:12:18.017609+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/VibeVoice"}, {"content_hash": "a784683f40081eb4874f60a8a447612fe875147f266d13337bb88ecc8b5f6934", "fetched_at": "2026-08-28T18:07:25.099994+00:00", "kind": "homepage", "missing": false, "url": "https://microsoft.github.io/VibeVoice/"}, {"content_hash": "b7b8a783e96d0df0421bb2d2751fb9ee14c25ac452d50432a96b48a83b521e81", "fetched_at": "2026-08-28T18:07:25.109002+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/vibevoice/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:19:34.204180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba850794c6d6a162f5eb1a801c147968034de0635e4cc665c6b16c4b56f1135b", "fetched_at": "2026-08-28T04:12:18.017609+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/VibeVoice"}, {"content_hash": "a784683f40081eb4874f60a8a447612fe875147f266d13337bb88ecc8b5f6934", "fetched_at": "2026-08-28T18:07:25.099994+00:00", "kind": "homepage", "missing": false, "url": "https://microsoft.github.io/VibeVoice/"}, {"content_hash": "b7b8a783e96d0df0421bb2d2751fb9ee14c25ac452d50432a96b48a83b521e81", "fetched_at": "2026-08-28T18:07:25.109002+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/vibevoice/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:19:34.204180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba850794c6d6a162f5eb1a801c147968034de0635e4cc665c6b16c4b56f1135b", "fetched_at": "2026-08-28T04:12:18.017609+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/VibeVoice"}, {"content_hash": "a784683f40081eb4874f60a8a447612fe875147f266d13337bb88ecc8b5f6934", "fetched_at": "2026-08-28T18:07:25.099994+00:00", "kind": "homepage", "missing": false, "url": "https://microsoft.github.io/VibeVoice/"}, {"content_hash": "b7b8a783e96d0df0421bb2d2751fb9ee14c25ac452d50432a96b48a83b521e81", "fetched_at": "2026-08-28T18:07:25.109002+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/vibevoice/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:18.017609+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:19:34.204180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba850794c6d6a162f5eb1a801c147968034de0635e4cc665c6b16c4b56f1135b", "fetched_at": "2026-08-28T04:12:18.017609+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/VibeVoice"}, {"content_hash": "a784683f40081eb4874f60a8a447612fe875147f266d13337bb88ecc8b5f6934", "fetched_at": "2026-08-28T18:07:25.099994+00:00", "kind": "homepage", "missing": false, "url": "https://microsoft.github.io/VibeVoice/"}, {"content_hash": "b7b8a783e96d0df0421bb2d2751fb9ee14c25ac452d50432a96b48a83b521e81", "fetched_at": "2026-08-28T18:07:25.109002+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/vibevoice/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:19:34.204180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba850794c6d6a162f5eb1a801c147968034de0635e4cc665c6b16c4b56f1135b", "fetched_at": "2026-08-28T04:12:18.017609+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/VibeVoice"}, {"content_hash": "a784683f40081eb4874f60a8a447612fe875147f266d13337bb88ecc8b5f6934", "fetched_at": "2026-08-28T18:07:25.099994+00:00", "kind": "homepage", "missing": false, "url": "https://microsoft.github.io/VibeVoice/"}, {"content_hash": "b7b8a783e96d0df0421bb2d2751fb9ee14c25ac452d50432a96b48a83b521e81", "fetched_at": "2026-08-28T18:07:25.109002+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/vibevoice/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:19:34.204180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba850794c6d6a162f5eb1a801c147968034de0635e4cc665c6b16c4b56f1135b", "fetched_at": "2026-08-28T04:12:18.017609+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/VibeVoice"}, {"content_hash": "a784683f40081eb4874f60a8a447612fe875147f266d13337bb88ecc8b5f6934", "fetched_at": "2026-08-28T18:07:25.099994+00:00", "kind": "homepage", "missing": false, "url": "https://microsoft.github.io/VibeVoice/"}, {"content_hash": "b7b8a783e96d0df0421bb2d2751fb9ee14c25ac452d50432a96b48a83b521e81", "fetched_at": "2026-08-28T18:07:25.109002+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/vibevoice/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:19:34.204180+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba850794c6d6a162f5eb1a801c147968034de0635e4cc665c6b16c4b56f1135b", "fetched_at": "2026-08-28T04:12:18.017609+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/VibeVoice"}, {"content_hash": "a784683f40081eb4874f60a8a447612fe875147f266d13337bb88ecc8b5f6934", "fetched_at": "2026-08-28T18:07:25.099994+00:00", "kind": "homepage", "missing": false, "url": "https://microsoft.github.io/VibeVoice/"}, {"content_hash": "b7b8a783e96d0df0421bb2d2751fb9ee14c25ac452d50432a96b48a83b521e81", "fetched_at": "2026-08-28T18:07:25.109002+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/vibevoice/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 94, "longevity": 26, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 373, "days_push": 40, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 60, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}