zs_tts.md

Zero Shot TTS

• Zero Shot TTS
  • Survey
  • Zero Shot TTS
  • Projects
  • Products
  • Datasets
  • Toolkits
  • Misc

Survey

Zero Shot TTS

• F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization, arXiv, 2504.02407, arxiv, pdf, cication: -1

  Xiaohui Sun, Ruitong Xiao, Jianye Mo, ..., Qun Yu, Baoxun Wang · (frontierlabs.github)

• Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens, arXiv, 2503.01710, arxiv, pdf, cication: -1

  Xinsheng Wang, Mingqi Jiang, Ziyang Ma, ..., Yike Guo, Wei Xue · (Spark-TTS - SparkAudio)

• IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System, arXiv, 2502.05512, arxiv, pdf, cication: -1

  Wei Deng, Siyi Zhou, Jingchen Shu, ..., Jinchao Wang, Lu Wang · (index-tts - index-tts)

• IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

• Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis, arXiv, 2502.04128, arxiv, pdf, cication: -1

  Zhen Ye, Xinfa Zhu, Chi-Min Chan, ..., Yike Guo, Wei Xue · (LLaSA_training - zhenye234)

• 🌟 Zonos-v0.1 is a leading open-weight text-to-speech model, delivering expressiveness and quality on par with—or even surpassing—top TTS providers. 🤗

• 🌟 CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models, arXiv, 2412.10117, arxiv, pdf, cication: -1

  Zhihao Du, Yuxuan Wang, Qian Chen, ..., Zhijie Yan, Jingren Zhou · (funaudiollm.github)

• Autoregressive Speech Synthesis with Next-Distribution Prediction, arXiv, 2412.16846, arxiv, pdf, cication: -1

  Xinfa Zhu, Wenjie Tian, Lei Xie · (zxf-icpc.github)

• 🌟 Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis, arXiv, 2411.01156, arxiv, pdf, cication: -1

  Shijia Liao, Yuxuan Wang, Tianyu Li, ..., Rongzhi Zhou, Yijin Xing · (fish-speech - fishaudio) · (𝕏)

• 🌟 Continuous Speech Synthesis using per-token Latent Diffusion, arXiv, 2410.16048, arxiv, pdf, cication: -1

  Arnon Turetzky, Nimrod Shabtay, Slava Shechtman, ..., Ron Hoory, Avihu Dekel · (s3.us-south.objectstorage.softlayer)

• MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer

• Continuous Speech Synthesis using per-token Latent Diffusion, arXiv, 2410.16048, arxiv, pdf, cication: -1

  Arnon Turetzky, Nimrod Shabtay, Slava Shechtman, ..., Ron Hoory, Avihu Dekel

• Parakeet A natural sounding, conversational text-to-speech model

Projects

• csm-voice-cloning - isaiahbjork

• Spark-TTS - SparkAudio

  An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens · (sparkaudio.github)

• F5-TTS - lpscr

  A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Products

• a new circular eye tracking device that uses ElevenLabs voices so people with ALS can generate speech with eye movement alone. 𝕏
• Generate a unique voice from a text prompt alone. 𝕏

Datasets

• Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation, arXiv, 2501.15907, arxiv, pdf, cication: -1

  Haorui He, Zengqiang Shang, Chaoren Wang, ..., Pengyuan Zhang, Zhizheng Wu · (huggingface)

Toolkits

Misc