VibeVoice-Realtime-0.5B — GGUF
Model variants
| File | Quant | Size | Notes |
|---|
vibevoice-realtime-0.5b-tts-f16.gguf | F16 | 2.0 GB | Full precision, reference quality |
vibevoice-realtime-0.5b-q8_0.gguf | Q8_0 | 1.2 GB | Near-lossless |
vibevoice-realtime-0.5b-q4_k.gguf | Q4_K | 699 MB | Recommended — perfect ASR round-trip |
The Q8_0/Q4_K files keep the diffusion prediction head, connectors and
EOS classifier at full precision (only the two Qwen2 backbones are
quantized). The head runs under classifier-free guidance over 20 solver
steps, so quantizing it could push the first frames onto a wrong
trajectory that decodes as a brief non-speech "music"/hum onset before
the voice; keeping it at full precision avoids that at a small size cost.
Voice prompts
A voice prompt is
required for TTS. Each
.gguf voice pack ships pre-computed KV caches that establish a fixed speaker identity (the realtime variant is
not WAV-cloning — for runtime cloning, use
cstr/vibevoice-1.5b-GGUF instead).
This repo bundles all 25 demo voices from
microsoft/VibeVoice@main demo/voices/streaming_model/ — same MIT license as the model.
| File | Speaker | Language |
|---|
vibevoice-voice-emma.gguf | Emma (F) | English (alias of en-Emma_woman) |
vibevoice-voice-en-Emma_woman.gguf | Emma (F) | English |
vibevoice-voice-en-Carter_man.gguf | Carter (M) | English |
vibevoice-voice-en-Davis_man.gguf | Davis (M) | English |
vibevoice-voice-en-Frank_man.gguf | Frank (M) | English |
vibevoice-voice-en-Grace_woman.gguf | Grace (F) | English |
vibevoice-voice-en-Mike_man.gguf | Mike (M) | English |
vibevoice-voice-de-Spk0_man.gguf | Spk0 (M) | German |
vibevoice-voice-de-Spk1_woman.gguf | Spk1 (F) | German |
vibevoice-voice-fr-Spk0_man.gguf | Spk0 (M) | French |
vibevoice-voice-fr-Spk1_woman.gguf | Spk1 (F) | French |
vibevoice-voice-in-Samuel_man.gguf | Samuel (M) | Indian English |
vibevoice-voice-it-Spk0_woman.gguf | Spk0 (F) | Italian |
vibevoice-voice-it-Spk1_man.gguf | Spk1 (M) | Italian |
vibevoice-voice-jp-Spk0_man.gguf | Spk0 (M) | Japanese |
vibevoice-voice-jp-Spk1_woman.gguf | Spk1 (F) | Japanese |
vibevoice-voice-kr-Spk0_woman.gguf | Spk0 (F) | Korean |
vibevoice-voice-kr-Spk1_man.gguf | Spk1 (M) | Korean |
vibevoice-voice-nl-Spk0_man.gguf | Spk0 (M) | Dutch |
vibevoice-voice-nl-Spk1_woman.gguf | Spk1 (F) | Dutch |
vibevoice-voice-pl-Spk0_man.gguf | Spk0 (M) | Polish |
vibevoice-voice-pl-Spk1_woman.gguf | Spk1 (F) | Polish |
vibevoice-voice-pt-Spk0_woman.gguf | Spk0 (F) | Portuguese |
vibevoice-voice-pt-Spk1_man.gguf | Spk1 (M) | Portuguese |
vibevoice-voice-sp-Spk0_woman.gguf | Spk0 (F) | Spanish |
vibevoice-voice-sp-Spk1_man.gguf | Spk1 (M) | Spanish |
Each voice pack is ~2-6 MB. The vibevoice-voice-emma.gguf filename is kept as the legacy default (referenced by crispasr -m auto --backend vibevoice-tts in CrispASR's auto-download manifest); vibevoice-voice-en-Emma_woman.gguf is the canonical upstream-named copy.
Usage
1# English with Emma
2crispasr --backend vibevoice-tts \
3 -m vibevoice-realtime-0.5b-q4_k.gguf \
4 --voice vibevoice-voice-emma.gguf \
5 --tts "Hello, how are you today?" \
6 --tts-output hello.wav
7
8# Japanese with jp-Spk1_woman
9crispasr --backend vibevoice-tts \
10 -m vibevoice-realtime-0.5b-q4_k.gguf \
11 --voice vibevoice-voice-jp-Spk1_woman.gguf \
12 --tts "こんにちは、これは日本語の音声テストです。" \
13 --tts-output jp.wav
Output: 24 kHz mono WAV. Use crispasr -m auto --backend vibevoice-tts to auto-download the model + the default Emma voice.
Runtime note: CrispASR keeps the initial sigma-VAE decoder samples for the
realtime model. Builds after 2026-06-18 also avoid spread-spectrum watermark
boundary amplification, fixing the earlier start-click artifact seen in some
short generated WAVs.
Architecture
VibeVoice-Realtime-0.5B is a streaming text-to-speech model:
- Base LM: 4-layer Qwen2 (text encoding with voice context)
- TTS LM: 20-layer Qwen2 (speech conditioning, autoregressive)
- Prediction head: 4 AdaLN + SwiGLU layers (flow matching denoiser)
- DPM-Solver++: 20-step 2nd-order midpoint solver (cosine schedule, v-prediction)
- Classifier-Free Guidance: dual KV cache, cfg_scale=3.0
- sigma-VAE decoder: 7-stage transposed ConvNeXt (3200× upsample to 24 kHz)
- EOS classifier: automatic length detection
Quality verification
All quantisations produce exact ASR round-trip matches on English:
| Input text | Parakeet ASR output |
|---|
| "Hello world" | "Hello world." |
| "Hello, how are you today?" | "Hello, how are you today?" |
| "The quick brown fox jumps over the lazy dog" | "The quick brown fox jumps over the lazy dog." |
| "Good morning everyone" | "Good morning, everyone." |
Decoder-start parity was also checked against the official PyTorch decoder by
replaying saved realtime latents: the C++ raw decoder output starts smoothly
and matches the reference onset profile before CLI watermarking and WAV
serialization.
Conversion
Model:
1python models/convert-vibevoice-to-gguf.py \
2 --input microsoft/VibeVoice-Realtime-0.5B \
3 --output vibevoice-realtime-0.5b-tts-f16.gguf \
4 --include-decoder
5
6build/bin/crispasr-quantize vibevoice-realtime-0.5b-tts-f16.gguf \
7 vibevoice-realtime-0.5b-q4_k.gguf q4_k
Voice packs (one per upstream .pt):
1python models/convert-vibevoice-voice-to-gguf.py \
2 --input demo/voices/streaming_model/en-Carter_man.pt \
3 --output vibevoice-voice-en-Carter_man.gguf
Attribution
- Original model:
microsoft/VibeVoice-Realtime-0.5B (MIT) — Microsoft Research.
- Voice packs: demo voices from
microsoft/VibeVoice@main (MIT).
- GGUF + ggml runtime:
CrispStrobe/CrispASR — see src/vibevoice.cpp, models/convert-vibevoice-to-gguf.py, and models/convert-vibevoice-voice-to-gguf.py.
License
MIT (same as the upstream model and voice prompts).
Provenance and EU AI Act Art. 53 note
- Upstream model: microsoft/VibeVoice-Realtime-0.5B — published by
microsoft.
- Upstream licence:
mit. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
- What was done here: format conversion and/or quantisation only (GGUF/GGML). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
- Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository.
- Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.
