Hugging Face launches Open TTS Leaderboard: objective metrics to rank 8K+ open TTS models
dl_weekly · x · 2026-10-16
Hugging Face team (Eric Bezzam, mrfakename, et al.) released an Open TTS Leaderboard with a detailed blog post on motivation and methodology:
- Context: over 8,000 TTS models on the HF Hub as of Sep 30, 2026, but evaluation remains fragmented and unstandardized.
- Why arenas fall short: TTS Arena v2, Artificial Analysis, and Voice Arena rank via human-preference Elo but can't scale with release velocity. Only 16 of 92 models on Artificial Analysis are open-weights — API models need just an API key while open models must be hosted by arena operators, and commercial providers have more incentive to seek placement. Voter consistency is also unenforceable.
- Solution: a leaderboard focused on open-source, multilingual TTS using objective metrics for scalable evaluation, covering voice cloning.
Recommended in this week's DL Weekly newsletter.
More from Multimodal
- USTC paper uses speculative sampling to cut latency in interactive video generation — ustc · 2026-10-16
- 800,000 Gaussian splats run in WebGPU; Casado sees near-infinite scaling — generativist · 2026-10-16
- Nano Banana 2.1 image generation now live in Perplexity Computer for all users — ChrisUniverse · 2026-10-16
- Demo shows precise camera-path control in 3D scenes from a single input image — XRarchitect · 2026-10-16
- Train Your Own LTX IC-LoRA With Grok Doing the Heavy Lifting — PurzBeats · 2026-10-16
- Flux 3 Klein excels at lighting and atmosphere but fumbles living subjects — Schattenmensch · 2026-10-16