VibeVoice (TTS code removed)
Source: https://github.com/microsoft/vibevoice
Structured fields
{
"archived": false,
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "Microsoft's open voice research framework. The TTS code was removed on 2025-09-05 after misuse; the repository now centres on VibeVoice-ASR (multilingual, streaming, BitNet CPU variants) and a realtime 0.5B model. A case study in withdrawn voice-synthesis release.",
"source_type": "repository",
"availability": "available",
"source_owner": "Microsoft",
"next_check_at": "2026-10-20T00:00:00.000Z",
"known_limitations": [
"TTS functionality withdrawn by the publisher."
],
"upstream_updated_at": "2026-10-08T05:29:29.000Z"
}Evidence claims
- [sourced_fact] README note dated 2025-09-05: after release, instances were found of the tool being used inconsistently with its stated intent, so the VibeVoice-TTS code was removed from the repository. · locator: README, 2025-09-05 notice source
- [sourced_fact] README release table: VibeVoice-ASR-7B, ASR-Streaming (2026-09-03), ASR-BitNet CPU (2026-07-23); VibeVoice-TTS-1.5B entry shows 'Disabled'; VibeVoice-Realtime-0.5B listed with Colab. · locator: README, news and model table source
- [sourced_fact] README states deepfake and disinformation risk of high-quality synthetic speech; LICENSE is MIT (Copyright 2025 Microsoft). · locator: README, risks section; LICENSE source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | MIT | permitted | permitted | permitted | unknown | MIT for the remaining repository code; TTS code removed. |
| model_weights | unknown | unknown | unknown | unknown | unknown | Model weights listed on Hugging Face were not inspected; TTS model entry marked Disabled. |