# Salesforce's SOV-Transcribe-1 tops open-weights speech-to-text at 2.3% AA-WER

> Artificial Analysis ranks Salesforce's SOV-Transcribe-1 as the top open-weights speech-to-text model at 2.3% AA-WER with 4.6B active parameters.

- Status: reported (One outlet, not independently verified yet.)
- Topic: Models
- Published: 2026-11-13T09:05:56+00:00
- Updated: 2026-11-13T09:11:02.139341+00:00
- Web page: https://ai-news.ikangai.com/story/salesforce-s-sov-transcribe-1-tops-open-weights-speech-to-text-at-2-3-aa-wer/
- Seen in: Latent Space
- Change: other (Other)
- Applies to: SOV-Transcribe-1

Artificial Analysis ranks Salesforce's SOV-Transcribe-1 as the top open-weights speech-to-text model, with a 2.3% AA-WER score and 4.6B active parameters. Word error rate measures the share of words a transcription model gets wrong, so lower is better. Active parameters are the share of a model's weights used when it processes an input.

The ranking rests on a single leaderboard result. Artificial Analysis is the only source cited, and no other transcription benchmark or independent test is reported.

## Why it matters

Teams building transcription pipelines get another open-weight option to benchmark, though the claim rests on one leaderboard.

---

AI wrote this summary from the sources listed, and nobody reviewed it individually before publication. Check the original source before you rely on it.

Cite as: IKANGAI AI News, "Salesforce's SOV-Transcribe-1 tops open-weights speech-to-text at 2.3% AA-WER", 2026-11-13, https://ai-news.ikangai.com/story/salesforce-s-sov-transcribe-1-tops-open-weights-speech-to-text-at-2-3-aa-wer/
