| Fish Audio S2 Technical Report | ✓ Link | 0.99 | | Fish Audio S2 | 2026-03-09 |
| AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing | ✓ Link | 1.02 | 0.788 | AuK | 2026-09-08 |
| AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing | ✓ Link | 1.03 | 0.772 | AuK-Flash | 2026-09-08 |
| Voxtral TTS | | 1.23 | 0.628 | Voxtral TTS | 2026-03-26 |
| Qwen3-TTS Technical Report | ✓ Link | 1.24 | | Qwen3-TTS-12Hz-1.7B-Base | 2026-01-22 |
| Qwen3.5-Omni Technical Report | | 1.26 | | Qwen3.5-Omni-Plus | 2026-04-21 |
| VoXtream2: Full-stream TTS with dynamic speaking rate control | ✓ Link | 1.32 | | VoXtream2 (462M) | 2026-03-13 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | 1.45 | | CosyVoice 3-1.5B RL | 2025-05-23 |
| Luna-TTS Family Technical Report | | 1.49 | 0.768 | Luna-TTS | 2026-08-12 |
| IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech | | 1.521 | 0.86 | IndexTTS2 | 2025-06-23 |
| ERNIE 5.0 Technical Report | | 1.54 | | ERNIE 5.0 | 2026-02-04 |
| ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching | ✓ Link | 1.62 | 0.67 | ZipVoice-Distill (8 NFE) | 2025-06-16 |
| MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder | | 1.65 | 0.692 | MiniMax-Speech | 2025-05-12 |
| Audio8 TTS Preview 0.1B | ✓ Link | 1.662 | 0.567 | Audio8 TTS Preview 0.1B | 2026-08-19 |
| ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching | ✓ Link | 1.7 | 0.697 | ZipVoice | 2025-06-16 |
| F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching | ✓ Link | 1.83 | 0.67 | F5-TTS (32 NFE) | 2024-10-09 |
| VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning | | 1.85 | 0.729 | VoxCPM | 2025-09-29 |
| Raon-Speech Technical Report | ✓ Link | 1.93 | | Raon-Speech | 2026-04-08 |
| Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens | ✓ Link | 1.98 | 0.584 | Spark-TTS | 2025-03-03 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | 2.19 | 0.71 | E2 TTS (32 NFE) | 2025-05-23 |
| Seed-TTS: A Family of High-Quality Versatile Speech Generation Models | ✓ Link | 2.249 | 0.762 | Seed-TTS ICL | 2024-06-04 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | 2.33 | 0.641 | Qwen2.5-Omni-7B RL | 2025-05-23 |
| CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models | ✓ Link | 2.38 | 0.654 | CosyVoice 2-S | 2024-12-13 |
| MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction | ✓ Link | 2.38 | | MiniCPM-o 4.5 | 2026-04-30 |
| MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer | ✓ Link | 2.623 | 0.717 | MaskGCT | 2024-09-01 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | 2.72 | 0.632 | Qwen2.5-Omni-7B | 2025-05-23 |
| VibeVoice Technical Report | ✓ Link | 3.04 | 0.689 | VibeVoice-1.5B | 2025-08-26 |
| CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training | ✓ Link | 3.82 | 0.46 | FireRedTTS | 2025-05-23 |
| CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models | ✓ Link | 4.29 | 0.609 | CosyVoice | 2024-12-13 |