| Fish Audio S2 Technical Report | ✓ Link | 0.54 | | Fish Audio S2 | 2026-03-09 |
| Luna-TTS Family Technical Report | | 0.73 | 0.797 | Luna-TTS | 2026-08-12 |
| Qwen3-TTS Technical Report | ✓ Link | 0.77 | | Qwen3-TTS-12Hz-1.7B-Base | 2026-01-22 |
| MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder | | 0.83 | 0.783 | MiniMax-Speech | 2025-05-12 |
| OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models | ✓ Link | 0.84 | 0.777 | OmniVoice | 2026-04-01 |
| MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction | ✓ Link | 0.86 | | MiniCPM-o 4.5 | 2026-04-30 |
| VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning | | 0.93 | 0.772 | VoxCPM | 2025-09-29 |
| IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech | | 1.008 | 0.865 | IndexTTS2 | 2025-06-23 |
| AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing | ✓ Link | 1.02 | 0.814 | AuK | 2026-09-08 |
| AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing | ✓ Link | 1.1 | 0.814 | AuK-Flash | 2026-09-08 |
| Seed-TTS: A Family of High-Quality Versatile Speech Generation Models | ✓ Link | 1.115 | 0.796 | Seed-TTS ICL | 2024-06-04 |
| Audio8 TTS Preview 0.1B | ✓ Link | 1.13 | 0.682 | Audio8 TTS Preview 0.1B | 2026-08-19 |
| OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models | ✓ Link | 1.14 | 0.778 | CosyVoice3 | 2026-04-01 |
| VibeVoice Technical Report | ✓ Link | 1.16 | 0.744 | VibeVoice-1.5B | 2025-08-26 |
| ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching | ✓ Link | 1.34 | 0.74 | ZipVoice-Distill (8 NFE) | 2025-06-16 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | 1.37 | 0.754 | F5R-TTS | 2025-05-23 |
| ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching | ✓ Link | 1.4 | 0.751 | ZipVoice | 2025-06-16 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | 1.42 | 0.754 | Qwen2.5-Omni-7B RL | 2025-05-23 |
| CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models | ✓ Link | 1.45 | 0.753 | CosyVoice 2-S | 2024-12-13 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | 1.51 | 0.635 | FireRedTTS | 2025-05-23 |
| F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching | ✓ Link | 1.56 | 0.76 | F5-TTS (32 NFE) | 2024-10-09 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | 1.7 | 0.752 | Qwen2.5-Omni-7B | 2025-05-23 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | 1.97 | 0.73 | E2 TTS (32 NFE) | 2025-05-23 |
| MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer | ✓ Link | 2.273 | 0.774 | MaskGCT | 2024-09-01 |
| CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models | ✓ Link | 3.63 | 0.723 | CosyVoice | 2024-12-13 |
| Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens | ✓ Link | | 0.672 | Spark-TTS | 2025-03-03 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | | 0.775 | CosyVoice 3-1.5B RL | 2025-05-23 |