eess.ASNov 10, 2026

Emilia2: A Large-Scale Dataset for Controllable Long-Form Speech Generation

Authors: Qinke Ni, Dekun Chen, Junwen Qiu, Huan Liao, Xu Li, Xingwen Han, Wan Lin, Kunyu Feng, 

Organizations: The Chinese University of Hong Kong, Shenzhen · University of Illinois at Urbana-Champaign

Abstract

Generating long-form speech requires models to keep content, speaker identity, turn-taking, and expressive style consistent over time. Yet most open training corpora contain examples lasting only tens of seconds and open long-form benchmarks cover at most two speakers per recording. We introduce Emilia2, a 229K-hour multilingual dataset for controllable long-form speech generation. From in-the-wild data, Emilia2 constructs short utterances, single-speaker long-form speech, and multi-speaker dialogues, preserving transcripts, speaker identities, pauses, and acoustic transitions. Examples longer than five minutes account for 50.0% of single-speaker long-form hours and 66.8% of dialogue hours. To support expressive control, Emilia2 provides natural language instructions for 4.77M examples and nonverbal-vocalization tags for 933K examples. We also introduce Emilia2-testset, 23 hours of bilingual recordings of up to 30 minutes and four speakers, each speaker paired with reference audio. We train autoregressive (AR) and non-autoregressive (NAR) models on Emilia2. Our 0.6B-backbone NAR model achieves the lowest Chinese CER and English WER on TTSD-Eval (5.27%/9.93%) among compared systems, while our AR model is on par with Qwen3-TTS-12Hz-VD on InstructTTSEval (zh/en: 76.2/78.3 vs. 77.1/77.9). These results validate Emilia2 as a comprehensive data foundation for long-form speech generation and minute-scale expressive control. Demo: https://charlesnii.github.io/Emilia2-demo/.

Figures & tables

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data

    Jun 16, 2026Subhankar Ghosh, Jason Li, Paarth Neekhara +4TTS SynthesisSpeech Prosody

  2. Speaking Longer Than Learned: Training-Free Long-Form Generation for Full-Stream Text-to-Speech

    Oct 14, 2026Jeseung Lim, Jiseong Woo, Heeseung KimLong-Form TTS SynthesisTTS Synthesis

  3. Post-Training Zero-Shot TTS for Fine-Grained Emotion and Duration Control via Natural Language

    Sep 10, 2026Lianru Gao, Yujie Guo, Yong QinTTS SynthesisZero-Shot TTS