mlsanityData to 7 Oct 2026

Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning

arXiv 2609.38658 ↗First posted 29 Sep 2026eess.AS cs.CL cs.SDcited by 0

Not on the map. Why?

Abstract (arXiv)

TTS systems with autoregressive semantic modeling have demonstrated strong zero-shot voice cloning performance and rich expressive variation, but their sequential decoding incurs substantial latency. Non-autoregressive alternatives offer much faster generation, yet often rely on more restrictive reference conditioning, such as requiring transcripts of the reference speech during inference. We present Tacit-TTS, an efficient transcript-free zero-shot voice cloning system distilled from IndexTTS2. Our model replaces autoregressive text-to-semantic decoding with masked non-autoregressive generation, introduces training-free acoustic length estimation, and accelerates the flow-matching renderer through ReFlow distillation. Across two English and two Mandarin datasets, Tacit-TTS achieves competitive zero-shot quality while generating speech over 10x faster than IndexTTS2 for utterances longer than 5 seconds. Its transcript-free conditioning further supports cross-lingual and non-lexical references. We validate this capability using references from eight other languages, infant babble, and synthetic gibberish, where transcript-dependent systems often degrade or fail due to unreliable ASR transcripts.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 42 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

36 of 42 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  7. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  8. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  9. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  10. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
  11. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  12. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
24 more
  1. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 458
  2. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 381
  3. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  4. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 364
  5. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 353
  6. 2021W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Trainingcited by 340
  7. 2024CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokenscited by 323
  8. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 293
  9. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 282
  10. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 277
  11. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 245
  12. 2023NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizerscited by 233
  13. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 222
  14. 2023Seamless: Multilingual Expressive and Streaming Speech Translationcited by 190
  15. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 159
  16. 2024E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTScited by 149
  17. 2020Seen and Unseen emotional style transfer for voice conversion with a new emotional speech datasetcited by 119
  18. 2023SoundStorm: Efficient Parallel Audio Generationcited by 111
  19. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokenscited by 109
  20. 2023CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Maskingcited by 95
  21. 2023FunASR: A Fundamental End-to-End Speech Recognition Toolkitcited by 92
  22. 2025IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speechcited by 85
  23. 2025IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech Systemcited by 27
  24. 2024Emotional Dimension Control in Language Model-Based Text-to-Speech: Spanning a Broad Spectrum of Human Emotionscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
  2. 2025Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Cloning and Speech Synthesis
  3. 2026Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder
  4. 2026Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer
  5. 2026X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning
  6. 2026LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling
  7. 2026PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual Voice Cloning and Inference-Time Model Fusion
  8. 2026Voxtral TTS