Hume launches first audio-native decision model that answers structured questions straight from recordings
testingcatalog · x · 2026-11-03
Hume AI unveiled what it calls the first audio-native decision model, with an Audio Decisions API waitlist now open.
- The model works on sound itself, picking up hesitant pauses and sighs without transcripts or per-task models.
- Users can ask multiple questions about a recording at once — yes/no, multiple-choice, scale, and timestamp answers — for use cases like customer-call emotion, language ID, and background-noise scoring.
- Claimed backing: 100M+ speech samples, 10+ years of emotion science research, 50+ languages, and adoption by 5 of 7 leading AI labs.
Related event: Hume AI launches Audio Decision API, an audio-native decision model(6 posts)→
More from Multimodal
- Cosmos 3 world model follows camera controls from a single image, recipe released — NVIDIAAI · 2026-11-03
- NVIDIA Cosmos recipes turn depth video into RGB scenes for robot and AV training — NVIDIAAI · 2026-11-03
- NVIDIA Cosmos Simulation Recipes Turn Daytime Drives Into Rainy Nights With Trajectories Intact — NVIDIAAI · 2026-11-03
- Suno user begs for a button that writes prompts so they never have to — gleech · 2026-11-03
- Seedance 2.5 demo: a 30-second swamp creature short film made in Dreamina — LudovicCreator · 2026-11-03
- Turning his photo library into drum samples with Gemini 4 — alexanderchen · 2026-11-03