Azure AI Speech LLM 09-2026 adds 25 languages, runs up to 2x faster and cuts entity error rate by up to 37%
A routine upgrade to the speech-to-text model that matters directly to teams building voice agents and multilingual transcription.
// Key points
- Adds 25 languages, including 11 Indic languages plus Catalan, Malay and Welsh, for 50 languages across 60+ locales in total.
- Across internal and public benchmarks such as GigaSpeech and VoxPopuli, token error rate improves by up to 25% and entity error rate by up to 37%, most on financial-domain entities.
- Up to 2x faster than 2607, especially for 5-10 second clips at high concurrency, with fewer hallucinations on silent or empty audio.
- Multilingual mode is the default: omit locale hints when one file mixes languages; hints are for genuinely single-language audio.
Builder's takeFor voice interviews, entity error rate is the number to watch: get a company or technology name wrong and every downstream score drifts. Mixed Chinese and English is common in AI Interview recordings, so I would drop the locale hint as advised, measure proper-noun errors on my own real recordings, and compare against the current setup rather than looking only at overall error rate.