Voila Autonomous Preview

🚀 Voila: Voice-Language Foundation Models

Voila is a new family of large voice - language foundation models. It aims to elevate human - AI interaction experiences. By breaking the constraints of traditional voice AI systems, such as high latency, loss of vocal nuances, and mechanical responses, Voila uses an innovative end - to - end model design and a novel hierarchical Transformer architecture. This enables real - time, autonomous, and rich voice interactions with low latency, and it excels in various audio tasks.

Voila: Voice-Language Foundation Models

Project Page    |    GitHub    |    Hugging Face   |    Paper    |    Online Demo   |    Maitrix.org

✨ Features

• High - fidelity, low - latency, real - time streaming audio processing
• Effective integration of voice and language modeling capabilities
• Millions of pre - built and custom voices, fast voice switching during conversation
• Unified model for various audio tasks

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

CLI demo

for model_name in "maitrix-org/Voila-audio-alpha" "maitrix-org/Voila-base" "maitrix-org/Voila-chat"; do
    # Text chat
    python infer.py \
        --model-name ${model_name} \
	    --instruction "" \
	    --input-text "Hello" \
	    --task-type chat_tito
    # Voice chat
    python infer.py \
        --model-name ${model_name} \
	    --instruction "" \
	    --input-audio "examples/test1.mp3" \
	    --task-type chat_aiao
done

# Autonomous mode
python infer.py \
    --model-name "maitrix-org/Voila-autonomous-preview" \
	--instruction "" \
	--input-audio "examples/test_autonomous1.mp3" \
	--task-type chat_aiao_auto

Gradio demo

python gradio_demo.py

For more information, please refer to the code repository.

📚 Documentation

Foundation Models

Datasets

Benchmark

1. Voila Benchmark

We introduce a novel speech evaluation benchmark called the Voila Benchmark. It is constructed by sampling from five widely used language model evaluation datasets: MMLU, MATH, OpenAI HumanEval, NQ - Open, and GSM8k. We compare our results with SpeechGPT and Moshi.

(higher is better)

For detailed scores of Voila Benchmark on each specific domain, please refer to our paper (Section 5.1 "Evaluation of Voila Benchmark").

2. Evaluation of ASR

As Voila supports multiple tasks, including Automatic Speech Recognition (ASR), Text - to - Speech (TTS), and spoken question answering, we also evaluate the performance of ASR and TTS. For ASR, we assess performance on the LibriSpeech test - clean dataset, using Word Error Rate (WER) as our metric. Voila attains a word error rate (WER) of 4.8%, outperforming the 5.7% reported by Moshi. In scenarios where both models utilize LibriSpeech training data, Voila achieves an impressive WER of 2.7%.

(lower is better)

3. Evaluation of TTS

For TTS, we follow the evaluation metrics proposed in Vall - E, which involves transcribing the generated audio using HuBERT - Large. Voila once again leads with a WER of 3.2% (and 2.8% when using LibriSpeech training data).

(lower is better)

📄 License

This project is licensed under the MIT license.

🔧 Technical Details

No specific technical details are provided in the original document, so this section is skipped.

📄 Citation

If you find our work helpful, please cite us.

@article{voila2025,
  author    = {Yemin Shi, Yu Shu, Siwei Dong, Guangyi Liu, Jaward Sesay, Jingwen Li, Zhiting Hu},
  title     = {Voila: Voice - Language Foundation Models for Real - Time Autonomous Interaction and Voice Roleplay},
  eprint={2505.02707},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  year      = {2025}
}