All tasks / Models
StepAudio 3 Realtime
StepFun's realtime speech-to-speech model served through its own API.
- StepFun
- Closed
Where it ranks
- –Voice agentsModels · Cloud · no result on this task’s benchmarks yet
Facts
- Vendor
- StepFun
- Family
- Step-Audio Realtime
- Released
- —
- Weights
- Closed: API and apps only
- License
- proprietary
- Last verified
- 18 Oct 2026
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Big Bench Audio (speech reasoning) | 99.7% | StepAudio 3 Realtime, StepFunBig Bench Audio speech reasoning (audio in, audio out); embedded value 0.997 as percent; no last-updated date shown. | 18 Oct 2026 | artificialanalysis.ai |
Where you can use it
No tracked tool lists this model yet.