OpenCodePapers

text-to-speech-synthesis-on-librispeech-pc-test-clean

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.
PaperCodeWERUTMOSSpeaker SimilarityModelNameReleaseDate
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching✓ Link1.514.050.657ZipVoice-Distill (4 NFE)2025-06-16
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models✓ Link1.594.280.694CosyVoice32026-04-01
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models✓ Link1.64.410.704Qwen3-TTS2026-04-01
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching✓ Link1.643.980.668ZipVoice2025-06-16
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models✓ Link1.744.180.717VoxCPM2026-04-01
Fish Audio Drama 3 Technical Report✓ Link1.854.31Fish Audio Drama 32026-10-13
VoXtream2: Full-stream TTS with dynamic speaking rate control✓ Link2.12VoXtream2 (462M)2026-03-13
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models✓ Link2.354.060.700IndexTTS22026-04-01
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching✓ Link2.423.90.66F5-TTS (32 NFE)2024-10-09
MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer✓ Link2.6340.687MaskGCT2024-09-01
Check out how to contribute new results. Then edit this file on GitLab or GitHub.