mlsanityData to 14 Oct 2026

VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency

arXiv 2509.15969 ↗First posted 19 Sep 2025eess.AS cs.CL cs.HCcited by 5

Not on the map. Why?

Abstract (arXiv)

We present VoXtream, a fully autoregressive, zero-shot streaming text-to-speech (TTS) system for real-time use that begins speaking from the first word. VoXtream directly maps incoming phonemes to audio tokens using a monotonic alignment scheme and a limited look-ahead that does not delay onset. Built around an incremental phoneme transformer, a temporal transformer predicting semantic and duration tokens, and a depth transformer producing acoustic tokens, VoXtream achieves, to our knowledge, the lowest initial delay among publicly available streaming TTS: 102 ms on GPU. Despite being trained on a mid-scale 9k-hour corpus, it matches or surpasses larger baselines on several metrics, while delivering competitive quality in both output- and full-streaming settings. Demo and code are available at https://herimor.github.io/voxtream.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 29 of its 36 references that are in the map. First posted on arXiv 19 Sep 2025.

Builds on

29 of 36 references.

References · 29

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  4. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  5. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
  6. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
  7. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 390
  8. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  9. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  10. 2024CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokenscited by 334
  11. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 288
  12. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 226
17 more
  1. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 204
  2. 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 192
  3. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
  4. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 161
  5. 2023Matcha-TTS: A fast TTS architecture with conditional flow matchingcited by 145
  6. 2024VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wildcited by 120
  7. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokenscited by 113
  8. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 70
  9. 2024VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignmentcited by 38
  10. 2025ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matchingcited by 30
  11. 2024Reshape Dimensions Network for Speaker Recognitioncited by 28
  12. 2025HiFiTTS-2: A Large-Scale High Bandwidth Speech Datasetcited by 10
  13. 2023Speak While You Think: Streaming Speech Synthesis During Text Generationcited by 8
  14. 2025SpeakStream: Streaming Text-to-Speech with Interleaved Datacited by 8
  15. 2024Zero-Shot Text-to-Speech from Continuous Text Streamscited by 7
  16. 2025FireRedTTS-1S: An Upgraded Streamable Foundation Text-to-Speech Systemcited by 6
  17. 2025VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimizationcited by 7
  2. 2026VoXtream2: Full-stream TTS with dynamic speaking rate controlcited by 3
  3. 2026VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agentscited by 3
  4. 2026What Counts as Real? Speech Restoration and Voice Quality Conversion Pose New Challenges to Deepfake Detectioncited by 0
  5. 2026X2-NativeCursor: Native-Token Text Progress Tracking for Incremental-Text Streaming Codec TTScited by 0