Aller au contenu

Microsoft VibeVoice 1.5B Microsoft · text-to-speech (TTS) API

Listener Elo 956 ±14 on Artificial Analysis (read October 22, 2026); latency not measured.

Benchmark summary: No speed tier: Coval, the source of the tiers, does not measure this model.

Microsoft VibeVoice 1.5B is an open-weights text-to-speech (TTS) API from Microsoft, measured by one independent benchmark, Artificial Analysis.

Speed tier

Not measured by Coval

No speed tier: Coval, the source of the tiers, does not measure this model.

Median time to first audioCoval, 30 days
—
P95 time to first audio (slow turns)Coval, 30 days
—
Naturalness EloSpeko
not rated
Listener Elo (95% interval)Artificial Analysis
956 ±14
Numbers and dates (0 to 1)Speko
not rated
List price per 1M charactersall sources
not published
  • Customer service (Artificial Analysis): 82nd, Elo 980 ±35

Data read October 22, 2026. No combined score: methodology

Gradium TTS vs Microsoft VibeVoice 1.5B Fastest TTS APIs, by speed tier

Speed

Neither Coval nor Speko measures Microsoft VibeVoice 1.5B's latency, so it has no speed tier and does not appear in the speed tiers.

Voice quality

In the Artificial Analysis Speech Arena it holds 956 ±14 Elo (95% interval), 83rd highest of the 98 models Artificial Analysis rates; scores whose intervals overlap are a tie. In its Customer Service category, Artificial Analysis places it 82nd, at 980 Elo.

Numbers and dates

Speko has not scored its pronunciation of numbers and dates.

Price

No list price is published by Coval, Speko or Artificial Analysis for this model.

Benchmark measurements

Artificial Analysis Speech Arena

Customer service rank
82
Customer service Elo
980
Customer service Elo 95% interval (±)
35
Speech Arena Elo (blind listener preference)
956
Elo 95% interval (±)
14
Arena rank
83
Arena rank range
83-86
Arena appearances
2,132
Voices tested
2
Released
Aug 2025
Artificial Analysis model
VibeVoice 1.5B
Artificial Analysis leaderboard
artificialanalysis.ai

Not collected

Similar TTS models