Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of Fish Audio: S2.1 Pro, Voxtral-Mini-3B-2507
2 modelsfish-audioFish Audio: S2.1 ProRemove ×mistralaiVoxtral-Mini-3B-2507Remove ×
What’s differentS2.1 Pro is a production-oriented text-to-speech model from Fish Audio. It is suited for multilingual voice applications, expressive narration, and dialogue synthesis, with open-ended natural-language…Voxtral Mini is an enhancement of Ministral 3B, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and…
DateJul 29, 2026ListedJul 19, 2025Listed
Listed rateSee provider quotes$16.6667 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗
Provider endpoints0 endpoints →2 endpoints →
AMI-Cleaned WER ↗English short-form; normalization unversionedNot reported13.57% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry
Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversionedNot reported7.66% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry
Gigaspeech-Cleaned WER ↗English short-form; normalization unversionedNot reported8.7% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry
LS Clean WER ↗English short-form; normalization unversionedNot reported1.48% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry
LS Other WER ↗English short-form; normalization unversionedNot reported3.63% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry
SPGISpeech WER ↗English short-form; normalization unversionedNot reported2.15% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry
URGENT2024 WER ↗English short-form; normalization unversionedNot reported15.66% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry
Voice Arena Monsoon WER ↗English short-form; normalization unversionedNot reported4.9% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry
Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversionedNot reported2.22% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry
Context window—32.8K
Max output——
Parameters—3B
Audio inputNot reportedSupported
TranscriptionNot reportedSupported
Open weightsNot reportedSupported

Add another model

Search all models →