#99th of 15 in Voice
vibevoice
Microsoft's open speech models for long-form ASR and streaming TTS
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 54.8k
- License
- MIT
- Last commit
- Oct 2026
- Language
- Python
23,512 on 24 Mar 202654,815 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
VibeVoice is a family of speech models built on 7.5 Hz continuous tokenizers and next-token diffusion. The ASR models transcribe up to 60 minutes of audio in one pass with speaker, timestamp and hotword support, plus a streaming variant and a CPU build. The TTS side includes a 0.5B real-time model with about 300 ms first-audio latency. The 1.5B long-form TTS code was removed from the repository after misuse.
Who it is for: Engineers needing local long-form transcription or streaming TTS
Strengths
- ASR handles 60 minutes in one pass, returning speaker, timestamps and text together
- Streaming ASR, vLLM serving and ASR fine-tuning code are documented
- BitNet CPU build shrinks ASR from 4.62 GB to 1.58 GB, RTF under 1 on 3+ threads
- Realtime TTS is 0.5B with about 300 ms first audible latency and streaming text input
Weaknesses
- VibeVoice-TTS code was removed; the 1.5B TTS model is listed as Disabled
- README says it is for research only, not recommended for commercial use
- Realtime TTS long-form output is about 10 minutes
- README gives no RAM or VRAM requirements for the full models
What it needs
- GPU optional
- Needs Hugging Face model weights, vLLM (optional, for serving)
- Models: VibeVoice-ASR-7B, VibeVoice-ASR-Streaming, VibeVoice-ASR-BitNet, VibeVoice-Realtime-0.5B, VibeVoice-TTS-1.5B
Also in Voice
See all 15| Rank | Project | Score |
|---|---|---|
| 1 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 74 out of 100 |
| 2 | VoiceboxLocal voice studio for cloning, TTS, dictation and agent speech | 69 out of 100 |
| 3 | Speech-to-SpeechModular voice-agent pipeline exposed through the OpenAI Realtime API | 66 out of 100 |
| #4 | Kokoro-FastAPIOpenAI-compatible text-to-speech server for the Kokoro-82M model | 65 out of 100 |
| #5 | Pocket TTSCPU-only text-to-speech model with voice cloning and streaming | 63 out of 100 |