🆕 GPA-TTS Updates
GPA-TTS is a standalone, ultra-efficient TTS runtime distilled from GPA, designed for edge deployment.
• INT8/INT4 quantized: among the smallest open-source TTS runtimes
• Runtime-selectable decoder: INT8 / FP16 / FP32 (quality vs. efficiency trade-off)
• Zero-shot voice cloning from short reference audio
• Fully local: no external LLM required
• Production-ready REST API with voice management
Built for developers deploying voice applications on resource-constrained devices.
📖 Abstract
GPA stands for General Purpose Audio.
In academia, a student’s GPA (Grade Point Average) serves as a unified metric that reflects performance across diverse subjects—ranging from Calculus and Philosophy to Gym class.
Similarly, our GPA model unifies the three major pillars of audio tasks—Text-to-Speech (TTS), Automatic Speech Recognition (ASR), and Voice Conversion (VC)—into a single auto-regreesive transformer.
- Our open-source content includes support for multiple frameworks and provides production-ready code suitable for cloud deployment.
- we include concise inference examples and training pipelines for research purpose.
- The released 0.3B model is also perfect for edge devices and edge deployment is to be released.
🔍 Model Overview
The following results are obtained by benchmarking services instantiated via the official deployment scripts, reflecting end-to-end performance in realistic serving scenarios rather than offline inference.
Among currently available open-source systems, our model is one of the few that natively supports both concurrent and streaming inference, while achieving performance comparable to the first tier of existing approaches.
💡Note
- TTFC: Time To First Chunk (TTS)
- TTFT: Time To First Token (ASR)
- RTF: Real-Time Factor (audio duration / synthesis time)
TTS Streaming Benchmark (Latency & Throughput)
ASR Streaming Benchmark
📊 Evaluation Metric Results
TTS Evaluation Table
Table with columns: Model, Open-Source, Model Size, test-zh CER (%) ↓, test-zh Sim (%) ↑, test-en WER (%) ↓, test-en Sim (%) ↑| Model | Open-Source | Model Size | test-zh CER (%) ↓ | test-zh Sim (%) ↑ | test-en WER (%) ↓ | test-en Sim (%) ↑ |
|---|
| Multi-Stage or NAR Methods | | | | | | |
| Human | - | - | 1.26 | 75.5 | 2.14 |
ASR Evaluation Table
Note: ASR results on Librispeech and Aishell-1. WER (%) is reported for Librispeech, and CER (%) is reported for Aishell-1.
Table with columns: Model, Model Size, Librispeech test-clean, Aishell-1| Model | Model Size | Librispeech test-clean | Aishell-1 |
|---|
| Models with < 0.5B parameters | | | |
| Whisper-S | 0.24B | 3.13 | - |
| GPA-0.3B-preview | 0.3B | 8.88 | 4.50 |
| Models with > 0.5B parameters | | | |
🙏 Acknowledgements
We borrowed a lot of code from the following excellent projects:
🔗 Citation
If you find GPA useful for your research or projects, please cite us:
@misc{cai2026unifyingspeechrecognitionsynthesis,
title={Unifying Speech Recognition, Synthesis and Conversion with Autoregressive Transformers},
author={Runyuan Cai and Yu Lin and Yiming Wang and Chunlin Fu and Xiaodong Zeng},
year={2026},
eprint={2601.10770},
archivePrefix={arXiv},
primaryClass={cs.SD},
url={https://arxiv.org/abs/2601.10770},
}