Audio / Speech-to-Text

Saarika v2.5

Speech-to-text model from Sarvam AI · released May 2025 · vendor-reported (not yet ranked on an independent leaderboard)

Unrankednot on an independent leaderboard yet
May 2025release

Specifications

API model id
saarika:v2.5

Notes

  • Earlier-generation Sarvam speech-to-text model, since superseded by the Saaras line.

How this is measured

AA-WER v2 (Speech-to-Text)

Word error rate, % of words transcribed incorrectly (lower is better)

Artificial Analysis Word Error Rate index for non-streaming transcription. AA-WER v2 combines three datasets: AA-AgentTalk (50%), VoxPopuli-Cleaned-AA (25%) and Earnings22-Cleaned-AA (25%). Measured independently on dedicated hardware.

Release & sources

Release
May 2025 (month precision)
Release source
Sarvam changelog, May 2025

More STT models from Sarvam AI