{"id":"sov-transcribe-1","slug":"sov-transcribe-1","name":"SOV-Transcribe-1","orgId":"salesforce","family":"sov-transcribe-1","releaseDate":null,"availability":"ga","openWeights":true,"license":null,"paramsTotal":26630656030,"paramsSource":"tracked","contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/blog/salesforce-sovereign-intelligence/sov-transcribe-1","hfRepo":null,"modalities":["audio"],"aliases":["SOV-Transcribe-1","sov transcribe 1","sov-transcribe-1","SOV Transcribe 1","SOV-Transcribe 1","Salesforce SOV-Transcribe-1","salesforce-sovereign-intelligence/SOV-Transcribe-1","Missionforce Sovereign AI SOV-Transcribe-1"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-15","announced":"2026-11-12","blurb":"Salesforce AI Research's open-weight speech-augmented language model for non-streaming automatic speech recognition. The official model card lists 26.6B total parameters (4.6B active), including a Whisper large-v3 audio encoder, an audio projector, and a Gemma 4 26B A4B mixture-of-experts decoder. It accepts up to 30 minutes of 16 kHz audio, optional natural-language instructions, and context biasing, and transcribes English, French, German, Spanish, Italian, Portuguese, and Dutch. Weights are ungated on Hugging Face at salesforce-sovereign-intelligence/SOV-Transcribe-1 under Apache 2.0, with a companion DFlash draft model for speculative decoding. No public self-serve API is stated.","api":"none","openWeights":"yes","params":{"text":"26.6B total (4.6B active), including the audio encoder","source":"Official SOV-Transcribe-1 model card","total":26630656030},"facts":[{"label":"Architecture","value":"Official model card: Whisper large-v3 audio encoder, audio projector, and Gemma 4 26B A4B mixture-of-experts decoder. Precision BF16, with the MoE router in FP32. Official card base models: openai/whisper-large-v3 and google/gemma-4-26B-A4B-it"},{"label":"Audio input","value":"Official model card: up to 30 minutes (tested); 16 kHz audio with optional text instructions and context; output is transcript text"},{"label":"Languages","value":"English, French, German, Spanish, Italian, Portuguese, and Dutch (official model card)"},{"label":"Controls","value":"Official card: natural-language instructions for verbatim or cleaned-up transcripts, punctuation, capitalization, and number formatting; context biasing by supplying names, domain vocabulary, or a short topic description"},{"label":"Weights","value":"Apache 2.0, ungated on Hugging Face at salesforce-sovereign-intelligence/SOV-Transcribe-1 (official card metadata license: apache-2.0; License section: Apache 2.0). Official launch blog: weights released on Hugging Face under Apache 2.0. A companion DFlash draft model for speculative decoding is at salesforce-sovereign-intelligence/SOV-Transcribe-1-DFlash; the official DFlash card says it cannot transcribe audio on its own"},{"label":"Inference","value":"Official card: vLLM (plugin in the repository for vLLM 0.32.0 until native support is released) and Hugging Face Transformers, with trust_remote_code modeling code in the repo"},{"label":"Hosted access","value":"No public self-serve API or lab playground is stated on the official card or launch blog. Official blog: developers and enterprises can deploy the weights on infrastructure they control"}],"claims":["Lab claim: self-reported official Artificial Analysis AA-WER Index 2.28% on the official model-card benchmark table and launch blog, which also report AA-AgentTalk 1.78, Earnings22-AA 4.06, and VoxPopuli-AA 1.50. The same official table and blog report Nemotron 3.5 Transcribe at 2.81% and Voxtral Small at 2.77% on the AA-WER Index.","Lab claim: self-reported official VoiceCodeBench (BeSimple) scores of Canonical Token/Entity Match 93.39, Task Success Rate 76.33, and WER 5.01 (official model-card table). The official launch blog rounds these to 93.4% of entities recovered and 76.3% of recordings passed.","Lab claim: self-reported 8.21% average word error rate on AppTek Call-Center Dialogues across 14 English accents, and 25.69% word error rate on HALAS, from the official model-card table and launch blog.","Lab claim: self-reported Preference-ASR preference-aware word error rate of 5.05% with instructions and 5.72% with no instructions (official model-card table and launch blog).","Lab claim: self-reported Contextual Earnings-22 keyword F1 of 71.9 with no keywords, 96.8 with the clip's keywords, and 94.0 with the full-call keyword list (official launch blog). The official table also reports word error rates of 12.42, 9.73, and 9.98 on those three conditions.","Lab claim: self-reported official model-card table, Open ASR English public-set mean word error rate 5.44 and Open ASR multilingual mean 4.88."],"sources":[{"kind":"lab","title":"Introducing Salesforce SOV-Transcribe-1 (official launch blog)","url":"https://huggingface.co/blog/salesforce-sovereign-intelligence/sov-transcribe-1","date":"2026-11-12"},{"kind":"repo","title":"SOV-Transcribe-1 on Hugging Face","url":"https://huggingface.co/salesforce-sovereign-intelligence/SOV-Transcribe-1","date":"2026-11-12"},{"kind":"lab","title":"Salesforce AI Research announcement on X","url":"https://x.com/SFResearch/status/2121092946254823642","date":"2026-11-12"},{"kind":"lab","title":"Marc Benioff announcement on X","url":"https://x.com/Benioff/status/2121077110488109147","date":"2026-11-12"}],"firstBenchmark":null},"organization":{"id":"salesforce","name":"Salesforce","slug":"salesforce","country":null,"url":"https://www.salesforce.com/ai-research","color":"#A39E8F","mark":"SA"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Nov 12, 2026; no independent results yet.","lead":"As of Nov 22, 2026, SOV-Transcribe-1 is pending benchmarks on isitsota: announced Nov 12, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}