arXiv AI August 11, 2026 By Yunpei Li, Xun Zhou, Jinchao Wang, Lu Wang, Yong Wu, Siyi Zhou, Yiquan Zhou, Yining Wang, Yaogen Yang, Zhetao Hu, Shiyao Duan, Jiacheng Xu, Bin Xia, Jingchen Shu

IndexTTS 2.5 Technical Report

Read the original on arXiv AI →

arXiv:2601. 03888v4 Announce Type: replace-cross Abstract: In prior work, we introduced IndexTTS 2, a zero-shot neural text-to-speech foundation model comprising two core components: a transformer-based Text-to-Semantic (T2S) module and a non-autoregressive Semantic-to-Mel (S2M) module, which together enable faithful emotion replication and establish the first autoregressive duration-controllable generative paradigm.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

Hugging Face Trending Papers

Aug 12

Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder

Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time.

llms multimodal benchmarks

arXiv AI

Jul 24

Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs

arXiv:2607. 21042v1 Announce Type: new Abstract: Autoregressive text-to-speech models achieve strong naturalness but suffer from slow inference due to sequential token generation, limiting their deployment in production applications that require low latency.

By Muyang Du, Shuang Yu, Junjie Lai

llms diffusion efficiency multimodal benchmarks

arXiv AI

Jul 8

Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs

arXiv:2601. 12494v3 Announce Type: replace-cross Abstract: Audio large language models (LLMs) enable unified speech understanding and generation, but adapting them to linguistically complex and dialect-rich settings such as Arabic-English remains challenging.

By Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury

llms nlp fine-tuning multimodal benchmarks

arXiv AI

Jun 29

Do Speech Emphasis Models Generalize across Languages and Emotions?

arXiv:2606. 27717v1 Announce Type: cross Abstract: Prosodic emphasis varies across languages, emotions, and speaking styles, yet existing emphasis detection models are largely trained and evaluated on monolingual neutral read speech.

By Megan Wei, Deepali Aneja, Jiaqi Su, Yunyun Wang, Haonan Chen, Zeyu Jin

benchmarks

arXiv Machine Learning

Aug 4

Domain-Specific Evaluation of Text-to-Speech Systems: A Multi-Metric Benchmarking Study

arXiv:2608. 02235v1 Announce Type: cross Abstract: Recent advances in neural text-to-speech (TTS) systems have substantially improved speech naturalness and intelligibility across many languages.

By Ali Jafar, Amal Sarmad, Shifa Yousaf, Maryam Bashir

llms multimodal benchmarks

arXiv AI

Jun 3

Efficient ASR Training with Conversations that Never Happened

arXiv:2606. 03957v1 Announce Type: cross Abstract: Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data.

By M\'at\'e Gedeon, P\'eter Mihajlik

llms multimodal benchmarks

Related stories

Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder

Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs

Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs

Do Speech Emphasis Models Generalize across Languages and Emotions?

Domain-Specific Evaluation of Text-to-Speech Systems: A Multi-Metric Benchmarking Study

Efficient ASR Training with Conversations that Never Happened