README.md

---
license: mit
tags:
- audio tokenizer
library_name: transformers
pipeline_tag: feature-extraction
---


# VibeVoice Acoustic Tokenizer

VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking.

A core innovation of VibeVoice is its use of continuous speech tokenizers (Acoustic and Semantic) operating at an ultra-low frame rate of 7.5 Hz. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a next-token diffusion framework, leveraging a Large Language Model (LLM) to understand textual context and dialogue flow, and a diffusion head to generate high-fidelity acoustic details.

The speech tokenizer is a key component for both VibeVoice [TTS](https://huggingface.co/microsoft/VibeVoice-1.5B) and [ASR](https://huggingface.co/microsoft/VibeVoice-ASR).

➡️ **Technical Report:** [VibeVoice Technical Report](https://arxiv.org/abs/2508.19205)

➡️ **Project Page:** [microsoft/VibeVoice](https://microsoft.github.io/VibeVoice)

<p align="left">
  <img src="figs/tokenizer_comparison.png" alt="Tokenizer Comparison" height="250px">
</p>


# Models

| Model | Context Length | Length (min) |  Weight |
|-------|----------------|----------|----------|
| VibeVoice-Realtime-0.5B | 8K | ~10 min | [HF link](https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B) |
| VibeVoice-1.5B | 64K | ~90 min | [HF link](https://huggingface.co/microsoft/VibeVoice-1.5B) |
| VibeVoice-ASR | 64K | ~60 min | [HF link](https://huggingface.co/microsoft/VibeVoice-ASR) |
| VibeVoice-AcousticTokenizer | - | - | This model |


# Usage

## Setup

Until the VibeVoice acoustic tokenizer is part of an official Transformers release, it can be used by installing from the source code:
```python
pip install git+https://github.com/huggingface/transformers.git
```

## Example

<details>
  <summary>Encoding and decoding</summary>

```python
import torch
from scipy.io import wavfile

from transformers import AutoFeatureExtractor, VibeVoiceAcousticTokenizerModel
from transformers.audio_utils import load_audio_librosa


model_id = "microsoft/VibeVoice-AcousticTokenizer"

# load model
feature_extractor = AutoFeatureExtractor.from_pretrained(model_id)
model = VibeVoiceAcousticTokenizerModel.from_pretrained(model_id, device_map="auto")
print("Model loaded on device:", model.device)
print("Model dtype:", model.dtype)

# load audio
audio = load_audio_librosa(
    "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Alice_woman.wav",
    sampling_rate=feature_extractor.sampling_rate,
)

# preprocess audio
inputs = feature_extractor(
    audio,
    sampling_rate=feature_extractor.sampling_rate,
    pad_to_multiple_of=3200,
).to(model.device, model.dtype)
print("Input audio shape:", inputs.input_values.shape)
# Input audio shape: torch.Size([1, 1, 224000])

with torch.no_grad():
    # set VAE sampling to False for deterministic output
    encoded_outputs = model.encode(inputs.input_values, sample=False)
    print("Latent shape:", encoded_outputs.latents.shape)
    # Latent shape: torch.Size([1, 70, 64])

    decoded_outputs = model.decode(**encoded_outputs)
    print("Reconstructed audio shape:", decoded_outputs.audio.shape)
    # Reconstructed audio shape: torch.Size([1, 1, 224000])

# Save audio
output_fp = "vibevoice_acoustic_tokenizer_reconstructed.wav"
wavfile.write(output_fp, feature_extractor.sampling_rate, decoded_outputs.audio.squeeze().float().cpu().numpy())
print(f"Reconstructed audio saved to : {output_fp}")
```

</details>

**Original audio**
<audio controls>
  <source src="https://hf.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Alice_woman.wav" type="audio/wav">
</audio>

**Encoded/decoded audio**
<audio controls>
  <source src="https://hf.co/datasets/bezzam/vibevoice_samples/resolve/main/example_output/vibevoice_acoustic_tokenizer_reconstructed.wav" type="audio/wav">
</audio>


<details>
  <summary>Streaming</summary>

For streaming ASR or TTS, where cached states need to be tracked, the `use_cache` parameter can be used when encoding or decoding audio:

```python
import torch
from scipy.io import wavfile

from transformers import AutoFeatureExtractor, VibeVoiceAcousticTokenizerModel
from transformers.audio_utils import load_audio_librosa


model_id = "microsoft/VibeVoice-AcousticTokenizer"


# load model
feature_extractor = AutoFeatureExtractor.from_pretrained(model_id)
model = VibeVoiceAcousticTokenizerModel.from_pretrained(model_id, device_map="auto")
print("Model loaded on device:", model.device)
print("Model dtype:", model.dtype)

# load audio
audio = load_audio_librosa(
    "https://huggingface.co/datasets/bezzam/vibevoice_samples/resolve/main/voices/en-Alice_woman.wav",
    sampling_rate=feature_extractor.sampling_rate,
)

# preprocess audio
inputs = feature_extractor(
    audio,
    sampling_rate=feature_extractor.sampling_rate,
    pad_to_multiple_of=3200,
).to(model.device, model.dtype)
print("Input audio shape:", inputs.input_values.shape)
# Input audio shape: torch.Size([1, 1, 224000])

# chache will be initialized after a first pass
encoder_cache = None
decoder_cache = None
with torch.no_grad():
    # set VAE sampling to False for deterministic output
    encoded_outputs = model.encode(inputs.input_values, sample=False, padding_cache=encoder_cache, use_cache=True)
    print("Latent shape:", encoded_outputs.latents.shape)
    # Latent shape: torch.Size([1, 70, 64])

    decoded_outputs = model.decode(encoded_outputs.latents, padding_cache=decoder_cache, use_cache=True)
    print("Reconstructed audio shape:", decoded_outputs.audio.shape)
    # Reconstructed audio shape: torch.Size([1, 1, 224000])

    # `padding_cache` can be extracted from the outputs for subsequent passes
    encoder_cache = encoded_outputs.padding_cache
    print("Number of cached encoder layers:", len(encoder_cache.per_layer_in_channels))
    # Number of cached encoder layers: 34
    decoder_cache = decoded_outputs.padding_cache
    print("Number of cached decoder layers:", len(decoder_cache.per_layer_in_channels))
    # Number of cached decoder layers: 34

# Save audio
output_fp = "vibevoice_acoustic_tokenizer_reconstructed.wav"
wavfile.write(output_fp, feature_extractor.sampling_rate, decoded_outputs.audio.squeeze().float().cpu().numpy())
print(f"Reconstructed audio saved to : {output_fp}")

```

</details>