Salesforce Releases SOV-Transcribe-1 Open-Weight Speech Recognition Model

Nov 14
1 min read
Salesforce released SOV-Transcribe-1 on November 12, 2026, an open-weight 26.6-billion-parameter speech recognition model distributed under the permissive Apache 2.0 license. Combining a Whisper audio encoder with a Mixture-of-Experts language backbone, the model enables local, non-streaming transcription with natural-language steering. For university researchers and research administration offices, local execution eliminates third-party cloud data exposure during interview transcription, establishing a secure alternative for institutional compliance.
Comments