# Artificial Analysis finds SOV-Transcribe-1 leads open-weights speech models on two datasets

> Original title: By dataset, SOV-Transcribe-1 leads open weights models on Earnings22 earnings calls (4.1% vs. Voxtral Small's 4.8%) and is slightly ahead...

- Source: Artificial Analysis
- Published: 2026-11-12T16:30:52.000Z
- Bad Influence: https://badinfluence.news/items/oapvl8mxxcrgypf57j89ci92e
- Original: https://x.com/ArtificialAnlys/status/2120917253210386551

## Summary

Artificial Analysis reports that Sovereign AI's SOV-Transcribe-1 leads open-weights models on Earnings22 earnings calls with a 4.1% error rate, versus 4.8% for Voxtral Small. It is also slightly ahead on VoxPopuli parliamentary speech at 1.5% versus 1.8%. On AA-AgentTalk, its voice agent conversations dataset, it scores 1.8%, level with Nemotron 3.5 Transcribe.

## Post

By dataset, SOV-Transcribe-1 leads open weights models on Earnings22 earnings calls (4.1% vs. Voxtral Small's 4.8%) and is slightly ahead on VoxPopuli parliamentary speech (1.5% vs. 1.8%). On AA-AgentTalk, our voice agent conversations dataset, it scores 1.8%, level with Nemotron 3.5 Transcribe

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHW8CVL3aEAAkKWi.jpg&mode=thumb&exp=1794787200&sig=a1448f1e0cd8f506)