# MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder

arXiv: https://arxiv.org/abs/2505.07916 · HTML: https://mlsanity.com/paper/2505.07916/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2025.

## Built on by (most cited first, 30 of 48)

- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models](https://mlsanity.com/paper/2604.00688/) (2026)
- [UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist](https://mlsanity.com/paper/2511.08521/) (2025)
- [Fish Audio S2 Technical Report](https://mlsanity.com/paper/2603.08823/) (2026)
- [Covo-Audio Technical Report](https://mlsanity.com/paper/2602.09823/) (2026)
- [Raon-Speech Technical Report](https://mlsanity.com/paper/2605.23912/) (2026)
- [MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speech](https://mlsanity.com/paper/2509.18196/) (2025)
- [IndexTTS 2.5 Technical Report](https://mlsanity.com/paper/2601.03888/) (2026)
- [RF-GPT: Teaching AI to See the Wireless World](https://mlsanity.com/paper/2602.14833/) (2026)
- [Exploiting Leaderboards for Large-Scale Distribution of Malicious Models](https://mlsanity.com/paper/2507.08983/) (2025)
- [Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Cloning and Speech Synthesis](https://mlsanity.com/paper/2509.14579/) (2025)
- [Dynin-Omni: Omnimodal Unified Large Diffusion Language Model](https://mlsanity.com/paper/2604.00007/) (2026)
- [Selective Classifier-free Guidance for Zero-shot Text-to-speech](https://mlsanity.com/paper/2509.19668/) (2025)
- [X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning](https://mlsanity.com/paper/2605.05611/) (2026)
- [dots.tts Technical Report](https://mlsanity.com/paper/2606.07080/) (2026)
- [TTS-1 Technical Report](https://mlsanity.com/paper/2507.21138/) (2025)
- [Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis](https://mlsanity.com/paper/2512.18699/) (2025)
- [Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis](https://mlsanity.com/paper/2601.13802/) (2026)
- [LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space](https://mlsanity.com/paper/2603.29339/) (2026)
- [Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis](https://mlsanity.com/paper/2505.12226/) (2025)
- [MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts](https://mlsanity.com/paper/2508.11326/) (2025)
- [Unifying Speech Recognition, Synthesis and Conversion with Autoregressive Transformers](https://mlsanity.com/paper/2601.10770/) (2026)
- [UniTalking: A Unified Audio-Video Framework for Talking Portrait Generation](https://mlsanity.com/paper/2603.01418/) (2026)
- [Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling](https://mlsanity.com/paper/2604.23586/) (2026)
- [Quantize More, Lose Less: Autoregressive Generation from Residually Quantized Speech Representations](https://mlsanity.com/paper/2507.12197/) (2025)
- [TeachMaster: Generative Teaching via Code](https://mlsanity.com/paper/2601.04204/) (2025)
- [DeepASMR: LLM-Based Zero-Shot ASMR Speech Generation for Anyone of Any Voice](https://mlsanity.com/paper/2601.15596/) (2026)

## Abstract (arXiv)

We introduce MiniMax-Speech, an autoregressive Transformer-based Text-to-Speech (TTS) model that generates high-quality speech. A key innovation is our learnable speaker encoder, which extracts timbre features from a reference audio without requiring its transcription. This enables MiniMax-Speech to produce highly expressive speech with timbre consistent with the reference in a zero-shot manner, while also supporting one-shot voice cloning with exceptionally high similarity to the reference voice. In addition, the overall quality of the synthesized audio is enhanced through the proposed Flow-VAE. Our model supports 32 languages and demonstrates excellent performance across multiple objective and subjective evaluations metrics. Notably, it achieves state-of-the-art (SOTA) results on objective voice cloning metrics (Word Error Rate and Speaker Similarity) and has secured the top position on the public TTS Arena leaderboard. Another key strength of MiniMax-Speech, granted by the robust and disentangled representations from the speaker encoder, is its extensibility without modifying the base model, enabling various applications such as: arbitrary voice emotion control via LoRA; text to voice (T2V) by synthesizing timbre features directly from text description; and professional voice cloning (PVC) by fine-tuning timbre features with additional data. We encourage readers to visit https://minimax-ai.github.io/tts_tech_report for more examples.