Downloads · 30 days
10
11% of all-time downloads
microsoft-vibevoice-0.5B-onnx-fp16
nenad1002/microsoft-vibevoice-0.5B-onnx-fp16
microsoft-vibevoice-0.5B-onnx-fp16 is a text-to-speech model from nenad1002. Use it when you need text read aloud. It is set up for vibevoice. The card lists the license as mit.
Microsoft's VibeVoice-Realtime-0.5B exported to ONNX format in FP16 precision with KV-cache support.
All-time downloads
92
Public
Repo size
1.9 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.onnx992 MB · 53%
At a glance
- Task
- Text-to-Speech
- Library
- vibevoice
- License
- mit
- Access
- Public
- Created
- Mar 17, 2026
- Updated
- Mar 17, 2026
- SHA
- 1227c4cb
Base models
Model card
From the Hugging Face model README
VibeVoice-Realtime-0.5B — ONNX FP16
Microsoft's VibeVoice-Realtime-0.5B exported to ONNX format in FP16 precision with KV-cache support.
Zero PyTorch dependency at inference time. Only requires: onnxruntime, numpy, soundfile, tokenizers.
Architecture
5 ONNX models forming the VibeVoice TTS pipeline:
| Model | Size | Description |
|---|---|---|
text_lm_kv.onnx | 374 MB | 4-layer Qwen2 text encoder with KV-cache |
tts_lm_kv.onnx | 572 MB | 20-layer Qwen2 TTS LM with KV-cache + EOS classifier |
diffusion_head.onnx | 81 MB | Latent denoiser (5-step DPM-Solver++) |
vocoder.onnx | 656 MB | Acoustic decoder (latents → 24kHz audio) |
acoustic_connector.onnx | 1.7 MB | Speech feedback projection |
Plus speaker voice presets (.npz files) and the inference script.
Usage
pip install onnxruntime numpy soundfile tokenizers
python vibevoice_full_onnx.py --text "Hello, this is a test." --speaker Carter
Options
python vibevoice_full_onnx.py \
--text "Your text here" \
--speaker Carter \
--output output.wav \
--cfg_scale 1.5
Available speakers: Carter, Frank, Emma, Grace, Davis, Mike, Wayne, and multilingual (de-Spk0, fr-Spk1, sp-Spk0, etc.)
Pipeline Flow
Text → [text_lm_kv] → hidden states
↓
[tts_lm_kv] ← [acoustic_connector] ← speech latent
↓
[diffusion_head] × 5 steps with CFG
↓
speech latent (64-dim)
↓
[vocoder] → audio (24kHz)
Export Details
- Exported from
microsoft/VibeVoice-Realtime-0.5Bin FP16 - Voice presets converted from BF16 → FP16
- DPM-Solver++ scheduler implemented in pure NumPy
- KV-cache passed as explicit inputs/outputs for stateful generation
- ONNX opset 18
License
MIT (same as original VibeVoice model)
- Task
- Text-to-Speech
- Library
- vibevoice
- License
- mit
- Created
- Mar 17, 2026
- Updated
- Mar 17, 2026