Audio / Text-to-Speech

VibeVoice 1.5B

Text-to-speech model from Microsoft Research & Azure · released Aug 2025

954Speech Arena Elo (±14)
#90-92rank range of 105
2,226blind votes
2 voicesvoices in the arena
Aug 2025release

95% confidence interval: Elo 940 – 968. 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
Aug 2025 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)

More TTS models from Microsoft Research & Azure