Audio / Text-to-Speech

MiMo-V2.5-TTS

Text-to-speech model from Xiaomi

1050Speech Arena Elo (±12)
#65-78rank range of 105
2,322blind votes
4 voicesvoices in the arena

95% confidence interval: Elo 1038 – 1062. Models whose intervals overlap share a rank range.

How this is measured

Speech Arena (Text-to-Speech)

Elo rating (higher is better)

Models are ranked with an Elo system derived from blind user votes: listeners hear two speech samples generated from the same text and pick the one that sounds more natural. The provider-voice leaderboard uses each provider's own native voices. Each result is reported with a 95% interval and the number of votes (samples).

Release & sources

Release
Not published