OpenCodePapers

text-to-speech-synthesis-on-seed-tts-test-hard

Speech SynthesisText-To-Speech Synthesis
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeCERSpeaker SimilarityModelNameReleaseDate
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training✓ Link5.090.75CosyVoice 3-0.5B RL2025-05-23
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing✓ Link5.910.782AuK2026-09-08
Fish Audio S2 Technical Report✓ Link5.99Fish Audio S22026-03-09
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing✓ Link6.430.784AuK-Flash2026-09-08
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training✓ Link6.540.752Qwen2.5-Omni-7B RL2025-05-23
CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models✓ Link6.830.724CosyVoice 22024-12-13
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training✓ Link7.590.776Seed-TTS2025-05-23
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training✓ Link7.970.747Qwen2.5-Omni-7B2025-05-23
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training✓ Link8.670.713F5-TTS (32 NFE)2025-05-23
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training✓ Link8.790.718F5R-TTS2025-05-23
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning8.870.73VoxCPM2025-09-29
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training✓ Link10.270.748MaskGCT2025-05-23
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training✓ Link11.750.709CosyVoice2025-05-23
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training✓ Link17.450.621FireRedTTS2025-05-23
Check out how to contribute new results. Then edit this file on GitLab or GitHub.