mlsanityData to 14 Oct 2026

Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

arXiv 2503.01710 ↗First posted 3 Mar 2025cs.SD cs.AI eess.AScited by 113

Not on the map. Why?

Cited by 28 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-stage processing or complex architectures for predicting multiple codebooks, limiting efficiency and integration flexibility. To overcome these challenges, we introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech codec that decomposes speech into two complementary token types: low-bitrate semantic tokens for linguistic content and fixed-length global tokens for speaker attributes. This disentangled representation, combined with the Qwen2.5 LLM and a chain-of-thought (CoT) generation approach, enables both coarse-grained control (e.g., gender, speaking style) and fine-grained adjustments (e.g., precise pitch values, speaking rate). To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations. Extensive experiments demonstrate that Spark-TTS not only achieves state-of-the-art zero-shot voice cloning but also generates highly customizable voices that surpass the limitations of reference-based synthesis. Source code, pre-trained models, and audio samples are available at https://github.com/SparkAudio/Spark-TTS.

Key facts. Cited by 113 papers in the map (data through 14 Oct 2026). Builds on 67 of its 94 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

67 of 94 references.

References · 67

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  6. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  7. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  8. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  9. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
  10. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 649
  11. 2018MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversationscited by 643
  12. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
38 more
  1. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
  2. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 476
  3. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 440
  4. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 431
  5. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 399
  6. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  7. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
  8. 2024CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokenscited by 334
  9. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 300
  10. 2022AudioGen: Textually Guided Audio Generationcited by 295
  11. 2023emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representationcited by 205
  12. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 204
  13. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
  14. 2020DDSP: Differentiable Digital Signal Processingcited by 178
  15. 2023Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modelingcited by 167
  16. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 161
  17. 2022Comparative layer-wise analysis of self-supervised speech modelscited by 158
  18. 2024VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizerscited by 122
  19. 2020Seen and Unseen emotional style transfer for voice conversion with a new emotional speech datasetcited by 121
  20. 2023Audiobox: Unified Audio Generation with Natural Language Promptscited by 120
  21. 2020AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselinescited by 111
  22. 2022PromptTTS: Controllable Text-to-Speech with Text Descriptionscited by 110
  23. 2023LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpuscited by 101
  24. 2023EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesiscited by 98
  25. 2022Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkitcited by 97
  26. 2023FunASR: A Fundamental End-to-End Speech Recognition Toolkitcited by 95
  27. 2021Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verificationcited by 78
  28. 2024Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Modelcited by 72
  29. 2022DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speechcited by 69
  30. 2024FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applicationscited by 68
  31. 2024Natural language guidance of high-fidelity text-to-speech with synthetic annotationscited by 67
  32. 2023SpeechX: Neural Codec Language Model as a Versatile Speech Transformercited by 64
  33. 2018The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systemscited by 61
  34. 2023VampNet: Music Generation via Masked Acoustic Token Modelingcited by 57
  35. 2022M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Databasecited by 50
  36. 2024Masked Audio Generation using a Single Non-Autoregressive Transformercited by 50
  37. 2024Scaling Transformers for Low-Bitrate High-Quality Speech Codingcited by 49
  38. 2023TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Modelscited by 48

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 53; 2026: 60.

113 papers.

Sort:

By area:

  1. 2025Qwen3-Omni Technical Reportcited by 497
  2. 2026Qwen3.5-Omni Technical Reportcited by 174
  3. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 150
  4. 2026Qwen3-TTS Technical Reportcited by 118
  5. 2025Step-Audio 2 Technical Reportcited by 105
  6. 2025IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speechcited by 90
  7. 2025EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Promptingcited by 34
  8. 2025ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matchingcited by 30
  9. 2025VibeVoice Technical Reportcited by 29
  10. 2026OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Modelscited by 25
  11. 2025EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judgecited by 24
  12. 2025SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Modelscited by 15
38 more
  1. 2025Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generationcited by 14
  2. 2026MOSS-TTS Technical Reportcited by 14
  3. 2025TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modelingcited by 13
  4. 2025DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesiscited by 8
  5. 2025Discrete Tokenization for Multimodal LLMs: A Comprehensive Surveycited by 8
  6. 2025ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matchingcited by 7
  7. 2025SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgementcited by 7
  8. 2025UniSS: Unified Expressive Speech-to-Speech Translation with Your Voicecited by 7
  9. 2025Step-Audio-EditX Technical Reportcited by 7
  10. 2026Stream-Voice-Anon: Enhancing Utility of Real-Time Speaker Anonymization via Neural Audio Codec and Language Modelscited by 7
  11. 2025FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancingcited by 6
  12. 2025M3-TTS: Multi-modal DiT Alignment & Mel-latent for Zero-shot High-fidelity Speech Synthesiscited by 6
  13. 2026UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Modelscited by 6
  14. 2026IndexTTS 2.5 Technical Reportcited by 6
  15. 2025OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactionscited by 5
  16. 2025VoXtream: Full-Stream Text-to-Speech with Extremely Low Latencycited by 5
  17. 2025From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modelingcited by 5
  18. 2026FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speechcited by 5
  19. 2025Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinesecited by 4
  20. 2025SpeechRole: A Large-Scale Dataset and Benchmark for Evaluating Speech Role-Playing Agentscited by 4
  21. 2025UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancementcited by 4
  22. 2025SpeechQualityLLM: LLM-Based Multimodal Assessment of Speech Qualitycited by 4
  23. 2026ActorMind: Emulating Human Actor Reasoning for Speech Role-Playingcited by 4
  24. 2025Multi-Reward GRPO for Stable and Prosodic Single-Codebook TTS LLMs at Scalecited by 3
  25. 2025Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesiscited by 3
  26. 2026Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesiscited by 3
  27. 2026FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenescited by 3
  28. 2026SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesiscited by 3
  29. 2026VoXtream2: Full-stream TTS with dynamic speaking rate controlcited by 3
  30. 2026LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Spacecited by 3
  31. 2026Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speechcited by 3
  32. 2025UDDETTS: Unifying Discrete and Dimensional Emotions for Controllable Emotional Text-to-Speechcited by 2
  33. 2025Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesiscited by 2
  34. 2025UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic informationcited by 2
  35. 2025MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Expertscited by 2
  36. 2025DiaMoE-TTS: A Unified IPA-Based Dialect TTS Framework with Mixture-of-Experts and Parameter-Efficient Zero-Shot Adaptationcited by 2
  37. 2025HiStyle: Hierarchical Style Embedding Predictor for Text-Prompt-Guided Controllable Speech Synthesiscited by 2
  38. 2025UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Modelscited by 2

50 most cited of 113 All 113 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025GOAT-TTS: Expressive and Realistic Speech Generation via A Dual-Branch LLM
  2. 2024ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering
  3. 2026TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment
  4. 2023Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias
  5. 2026CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
  6. 2025Towards Lightweight and Stable Zero-shot TTS with Self-distilled Representation Disentanglement
  7. 2025Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers
  8. 2025VocalNet-M2: Advancing Low-Latency Spoken Language Modeling via Integrated Multi-Codebook Tokenization and Multi-Token Prediction