Salesforce opens SOV-Transcribe-1, but active parameters are not the whole deployment bill
Salesforce opens SOV-Transcribe-1, but active parameters are not the whole deployment bill
Event/source dates: 2026-11-12 release announcement; exact time unknown
Salesforce released SOV-Transcribe-1 on November12 as an Apache 2.0 open-weight model for non-streaming speech transcription. The release lets developers steer transcript formatting and provide vocabulary context. That makes it a candidate for controlled dictation and document-transcription systems, not just generic speech recognition. Announcement
There is an important sizing distinction. The announcement describes four billion active and 26 billion total parameters; the model card specifies 4.6 billion active and 26.6 billion total including the audio encoder. It combines a Whisper large-v3 audio encoder with Gemma 4 26B A4B, and lists seven supported languages. Model card
Integration is not yet frictionless. The card says native framework support is being upstreamed; its current vLLM path uses a plugin, while Transformers uses the repository’s modeling code. This run did not install either route.
Analysis: count the resident model, not just the busy experts
Active parameter counts describe the work selected for a token, not the complete memory footprint. A buyer comparing this release with a small dense speech model should not mistake the four-billion headline for a four-billion-weight download or a guaranteed laptop fit. Quantization, framework overhead, the audio encoder and workload concurrency all belong in a deployment test.
The more useful product distinction is control over the transcript. A clean message and a verbatim record are different outputs. Teams should test whether requested formatting preserves names, numbers and meaning, rather than assuming prettier text is more accurate.
Benchmarks and limits
Salesforce claims strong leaderboard performance, but this article does not adopt its ranking as an independently verified conclusion. Artificial Analysis’s directly read methodology describes a weighted non-streaming benchmark across roughly eight hours of three datasets. That is useful context, not a guarantee for a particular company’s accents, vocabulary or critical identifiers. Benchmark methodology
Sources actually cited
Primary evidence
- Salesforce launch announcement: 2026-11-12. Directly read; release date, non-streaming scope and license
- SOV-Transcribe-1 model card: Current page checked 2026-11-13 UTC; update time unknown. Directly read; encoder-inclusive sizing and plugin/upstreaming boundary
Independent reporting or methodology
- Artificial Analysis non-streaming benchmark: Dynamic page checked 2026-11-13 UTC. Directly read methodology only; no independently verified model rank asserted
Sources and citations
Revision history
Published .