# IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities

arXiv: https://arxiv.org/abs/2410.08035 · HTML: https://mlsanity.com/paper/2410.08035/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 45 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 30 of 36)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling](https://mlsanity.com/paper/2402.12226/) (2024)
- [LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning](https://mlsanity.com/paper/2311.18651/) (2023)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision](https://mlsanity.com/paper/2302.03540/) (2023)
- [Direct speech-to-speech translation with discrete units](https://mlsanity.com/paper/2107.05604/) (2021)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)

## Built on by (most cited first, 17 of 17)

- [WavChat: A Survey of Spoken Dialogue Models](https://mlsanity.com/paper/2411.13577/) (2024)
- [LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis](https://mlsanity.com/paper/2505.02625/) (2025)
- [Recent Advances in Discrete Speech Tokens: A Review](https://mlsanity.com/paper/2502.06490/) (2025)
- [XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs](https://mlsanity.com/paper/2506.23325/) (2025)
- [VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation](https://mlsanity.com/paper/2504.04060/) (2025)
- [WavReward: Spoken Dialogue Models With Generalist Reward Evaluators](https://mlsanity.com/paper/2505.09558/) (2025)
- [Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective](https://mlsanity.com/paper/2412.17048/) (2024)
- [PredGen: Accelerated Inference of Large Language Models through Input-Time Speculation for Real-Time Speech Interaction](https://mlsanity.com/paper/2506.15556/) (2025)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations](https://mlsanity.com/paper/2506.09349/) (2025)
- [LTS-VoiceAgent: A Listen-Think-Speak Framework for Efficient Streaming Voice Interaction via Semantic Triggering and Incremental Reasoning](https://mlsanity.com/paper/2601.19952/) (2026)
- [WavBench: Benchmarking Reasoning, Colloquialism, and Paralinguistics for End-to-End Spoken Dialogue Models](https://mlsanity.com/paper/2602.12135/) (2026)
- [BayLing-Duplex: Native Full-Duplex Speech Dialogue with a Single Autoregressive LLM](https://mlsanity.com/paper/2606.14528/) (2026)
- [Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction](https://mlsanity.com/paper/2507.09834/) (2025)
- [Audio-Visual Intelligence in Large Foundation Models](https://mlsanity.com/paper/2605.04045/) (2026)
- [Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models](https://mlsanity.com/paper/2609.15759/) (2026)
- [ATIR: Towards Audio-Text Interleaved Contextual Retrieval](https://mlsanity.com/paper/2604.20267/) (2026)

## Abstract (arXiv)

Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational overhead and increases latency in multi-turn interactions. To address this, we introduce IntrinsicVoic,e an LLM designed with intrinsic real-time voice interaction capabilities. IntrinsicVoice aims to facilitate the transfer of textual capabilities of pre-trained LLMs to the speech modality by mitigating the modality gap between text and speech. Our novelty architecture, GroupFormer, can reduce speech sequences to lengths comparable to text sequences while generating high-quality audio, significantly reducing the length difference between speech and text, speeding up inference, and alleviating long-text modeling issues. Additionally, we construct a multi-turn speech-to-speech dialogue dataset named method-500k which includes nearly 500k turns of speech-to-speech dialogues, and a cross-modality training strategy to enhance the semantic alignment between speech and text. Experimental results demonstrate that IntrinsicVoice can generate high-quality speech response with latency lower than 100ms in multi-turn dialogue scenarios. Demos are available at https://instrinsicvoice.github.io/.