Tag

#speech-to-text

4 articles

Google AI Releases Gemini 3.5 Transcribe: A Speech-to-Text Model Reporting 2.6% Average WER Across 85+ Languages

This article explains Google's new Gemini 3.5 Transcribe speech-to-text model, detailing its dual-endpoint architecture, technical mechanisms, and implications for developers building voice agents and transcription systems.

Aug 2727

Google's Gemini 3.5 Transcribe turns speech to text in 85 languages while auto-correcting your verbal stumbles

Google's new Gemini 3.5 Transcribe supports 85 languages and features real-time auto-correction of verbal stumbles with a 4.0% word error rate.

Aug 2750

Microsoft AI Introduces MAI-Transcribe-1.5: 2.4% WER on Artificial Analysis, Best-in-Class FLEURS Accuracy, and Up to 5x Faster Long-Audio Transcription

This article explains speech-to-text technology and how Microsoft's new MAI-Transcribe-1.5 model improves speed, accuracy, and language support for converting spoken words into text.

Jun 787

Microsoft's MAI-Transcribe-1 runs 2.5x faster than its predecessor at $0.36 per audio hour

Microsoft's new MAI-Transcribe-1 model runs 2.5x faster than its predecessor and costs just $0.36 per audio hour, making it a powerful tool for transcription across 25 languages.

Apr 2103