Pith. sign in

REVIEW 28 cited by

IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.05512 v1 pith:YTAC3FXO submitted 2025-02-08 cs.SD cs.AIeess.AS

classification cs.SDcs.AIeess.AS
keywords characterscloningcontrollableindexttssystemsvoicezero-shotimprovements
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, large language model (LLM) based text-to-speech (TTS) systems have gradually become the mainstream in the industry due to their high naturalness and powerful zero-shot voice cloning capabilities.Here, we introduce the IndexTTS system, which is mainly based on the XTTS and Tortoise model. We add some novel improvements. Specifically, in Chinese scenarios, we adopt a hybrid modeling method that combines characters and pinyin, making the pronunciations of polyphonic characters and long-tail characters controllable. We also performed a comparative analysis of the Vector Quantization (VQ) with Finite-Scalar Quantization (FSQ) for codebook utilization of acoustic speech tokens. To further enhance the effect and stability of voice cloning, we introduce a conformer-based speech conditional encoder and replace the speechcode decoder with BigVGAN2. Compared with XTTS, it has achieved significant improvements in naturalness, content consistency, and zero-shot voice cloning. As for the popular TTS systems in the open-source, such as Fish-Speech, CosyVoice2, FireRedTTS and F5-TTS, IndexTTS has a relatively simple training process, more controllable usage, and faster inference speed. Moreover, its performance surpasses that of these systems. Our demos are available at https://index-tts.github.io.

Discussion (0). Sign in to comment.

Forward citations

Cited by 28 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model

    cs.SD 2026-06 unverdicted novelty 7.0 of 10

    FlexiSLM is the first spoken language model supporting dynamic and controllable frame rates on speech input and output, outperforming fixed-rate 7B models at high quality and enabling faster inference at lower rates l...

  2. MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech

    eess.AS 2026-04 unverdicted novelty 7.0 of 10

    MINT-Bench is a new benchmark using hierarchical taxonomy, multi-stage data pipeline, and hybrid evaluation to assess instruction-following TTS systems, revealing major gaps in compositional and paralinguistic controls.

  3. AST: Adaptive, Seamless, and Training-Free Precise Speech Editing

    cs.SD 2026-04 unverdicted novelty 7.0 of 10

    AST enables seamless speech editing by latent recomposition on pre-trained TTS models plus adaptive weak fact guidance, plus a new dataset and WDTW metric, claiming 70% WER reduction and better temporal consistency wi...

  4. EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection

    eess.AS 2025-10 unverdicted novelty 7.0 of 10

    EchoFake is a new replay-aware dataset combining zero-shot TTS deepfakes and physical replay recordings to improve generalization of speech deepfake detection models over existing lab-focused datasets.

  5. UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling

    cs.SD 2026-06 unverdicted novelty 6.0 of 10

    UniSAE unifies speaker, emotion, and multi-granularity content editing in speech via a new discrete phonetic posteriorgram representation and diffusion-based rendering.

  6. Joycent: Diffusion-based Accent TTS without Accented Phone Prediction

    cs.SD 2026-06 unverdicted novelty 6.0 of 10

    Joycent uses diffusion modeling and conditional layer normalization to synthesize accented speech from standard phones and references, claiming better accentedness and speaker preservation than two-stage baselines.

  7. Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy

    eess.AS 2026-06 unverdicted novelty 6.0 of 10

    READ is a reference-free ASR hypothesis scorer that measures acoustic discrepancy via conditional likelihood from a pretrained auto-regressive TTS model and yields up to 20% relative error rate reduction when used for...

  8. UniVocal: Unified Speech-Singing Code-Switching Synthesis

    cs.SD 2026-06 unverdicted novelty 6.0 of 10

    UniVocal presents a text-context-only framework for speech-singing code-switching synthesis via two-stage curriculum learning and a synthetic data pipeline, claiming SOTA on a new benchmark.

  9. Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    Agentic ASR adds closed-loop semantic correction to ASR and introduces S²ER, an LLM judge for meaning-level errors, showing larger gains on semantic than token metrics across multilingual benchmarks.

  10. SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis

    eess.AS 2026-05 unverdicted novelty 6.0 of 10

    SemaVoice adds SFM-guided alignment to refine continuous speech representations in autoregressive TTS, reporting 1.71% English WER on Seed-TTS and competitiveness with open-source SOTA.

  11. AST: Adaptive, Seamless, and Training-Free Precise Speech Editing

    cs.SD 2026-04 conditional novelty 6.0 of 10

    AST performs training-free text-based speech editing by stitching inverted source latents with synthesized targets and adaptively guiding the flow-matching decoder, achieving state-of-the-art temporal fidelity and spe...

  12. OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    OmniVoice introduces a diffusion language model-style non-autoregressive TTS system that directly maps text to multi-codebook acoustic tokens, scaling zero-shot synthesis to over 600 languages with SOTA results on mul...

  13. DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration

    cs.SD 2025-09 conditional novelty 6.0 of 10

    DiTReducio is a training-free, pattern-guided layer and branch skipping method that accelerates DiT-based TTS, reporting significant FLOP and RTF reductions with modest quality loss at tuned thresholds.

  14. ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching

    eess.AS 2025-07 conditional novelty 6.0 of 10

    ZipVoice-Dialog is a flow-matching non-autoregressive model for zero-shot spoken dialogue generation that uses curriculum learning and speaker-turn embeddings, paired with a new 6.8k-hour OpenDialog dataset, and repor...

  15. CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training

    cs.SD 2025-05 unverdicted novelty 6.0 of 10

    CosyVoice 3 achieves better content consistency, speaker similarity, and prosody naturalness in zero-shot multilingual speech synthesis by scaling data to one million hours, model size to 1.5 billion parameters, and i...

  16. X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System

    eess.AS 2026-07 conditional novelty 5.0 of 10

    An open, modular cascaded system (streaming ASR + MT + prompt-conditioned TTS) preserves speaker identity in long-form multi-speaker translation, at higher latency and slightly lower translation quality than proprietary APIs.

  17. AutoSIFT: Automatic Style Sifting for Controllable Speech Generation with Arbitrary Style Infilling

    cs.SD 2026-07 unverdicted novelty 5.0 of 10

    AutoSIFT disentangles text-describable style categories from residual speech styles and selectively infills only the categories the user specifies.

  18. AutoSIFT: Automatic Style Sifting for Controllable Speech Generation with Arbitrary Style Infilling

    cs.SD 2026-07 conditional novelty 5.0 of 10

    A TTS framework that replaces only text-specified style categories and infills all unspecified and residual style from a reference speech recording.

  19. AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    AgentSteerTTS proposes a multi-agent framework with adversarial disentanglement, dual-stream anchoring via acoustic prototypes, and fast-slow feedback to achieve intent-faithful expressive TTS for composite instructions.

  20. RoboKA: KAN Informed Multimodal Learning for RoboCall Surveillance System

    cs.MM 2026-04 unverdicted novelty 5.0 of 10

    RoboKA is a KAN-based multimodal fusion model that outperforms baselines on a new synthetic dataset for detecting adversarial robocalls via acoustic and linguistic cues.

  21. ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing

    cs.SD 2026-04 unverdicted novelty 5.0 of 10

    ActorMind is a four-agent chain-of-thought framework that emulates human actors to produce spontaneous, emotion-infused speech responses for role-playing scenarios.

  22. Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition

    cs.CL 2026-04 unverdicted novelty 5.0 of 10

    The authors introduce LLM-based semantic judgment and an agentic interaction loop that improves semantic fidelity and enables iterative corrections in automatic speech recognition beyond traditional WER.

  23. WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models

    cs.CL 2026-03 unverdicted novelty 5.0 of 10

    WAND converts full-attention AR-TTS models to global-plus-sliding-window attention with curriculum fine-tuning and teacher distillation, claiming quality preservation with up to 66.2% KV-cache savings and near-constan...

  24. WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models

    cs.CL 2026-03 unverdicted novelty 5.0 of 10

    WAND adapts AR-TTS models to constant complexity via windowed attention and distillation, cutting KV cache memory by up to 66.2% while preserving quality and achieving length-invariant latency.

  25. FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot

    cs.SD 2025-09 conditional novelty 5.0 of 10

    FireRedTTS-2 generates long multi-speaker conversations in a streaming, sentence-by-sentence way using a new low-rate speech tokenizer and a dual-transformer text-speech model.

  26. PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis

    cs.SD 2026-05 unverdicted novelty 4.0 of 10

    PilotTTS achieves lowest WER 1.50% (en) and CER 0.87% (zh) plus highest speaker similarity on Seed-TTS Eval using a Q-Former conditioned autoregressive architecture and a released multi-stage open data pipeline.

  27. Robust Residual Finite Scalar Quantization for Neural Compression

    eess.IV 2025-08 reject novelty 4.0 of 10

    RFSQ applies learned scaling or invertible LayerNorm to residual FSQ to prevent magnitude decay, reporting DNSMOS and image loss gains, though the LayerNorm variant has a reconstruction inconsistency.

  28. AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan

    cs.SD 2026-04 unverdicted novelty 3.0 of 10

    AT-ADD introduces standardized tracks and datasets for evaluating audio deepfake detectors on speech under real-world conditions and on diverse unknown audio types to promote generalization beyond speech-centric methods.

Pith tools