mlsanityData to 7 Oct 2026

TTS-1 Technical Report

arXiv 2507.21138 ↗First posted 22 Jul 2025cs.CL cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

We introduce Inworld TTS-1, a set of two Transformer-based autoregressive text-to-speech (TTS) models. Our largest model, TTS-1-Max, has 8.8B parameters and is designed for utmost quality and expressiveness in demanding applications. TTS-1 is our most efficient model, with 1.6B parameters, built for real-time speech synthesis and on-device use cases. By scaling train-time compute and applying a sequential process of pre-training, fine-tuning, and RL-alignment of the speech-language model (SpeechLM) component, both models achieve state-of-the-art performance on a variety of benchmarks, demonstrating exceptional quality relying purely on in-context learning of the speaker's voice. Inworld TTS-1 and TTS-1-Max can generate high-resolution 48 kHz speech with low latency, and support 11 languages with fine-grained emotional control and non-verbal vocalizations through audio markups. We additionally open-source our training and modeling code under an MIT license.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 34 of its 42 references that are in the map. First posted on arXiv 22 Jul 2025.

Builds on

34 of 42 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2024The Llama 3 Herd of Modelscited by 14,192
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  7. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  8. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  9. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  10. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  11. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  12. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
22 more
  1. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,276
  2. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  3. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
  4. 2022High Fidelity Neural Audio Compressioncited by 673
  5. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 641
  6. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 621
  7. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
  8. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  9. 2024CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokenscited by 323
  10. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 293
  11. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 282
  12. 2024RedPajama: an Open Dataset for Training Large Language Modelscited by 178
  13. 2021DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressorscited by 165
  14. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
  15. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 142
  16. 2021The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usagecited by 98
  17. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 69
  18. 2023Better speech synthesis through scalingcited by 63
  19. 2024BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codeccited by 45
  20. 2025MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encodercited by 44
  21. 2024Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedbackcited by 19
  22. 2023Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Modelscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTScited by 3
  2. 2026Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecscited by 0
  3. 2026NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-Speechcited by 0