Last refreshed 2026-06-29. Next refresh: weekly.
Why use StepAudio 2.5 Realtime on StepFun?
StepFun offers StepAudio 2.5 Realtime with competitive pricing. StepFun is a Chinese AI company providing API access to its Step series of large language and multimodal models.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: step-2.5-realtimestep-2.5-realtimeRequest example
step-2.5-realtime.Gotchas
- Use provider model ID "step-2.5-realtime", not the LLMReference slug "step-audio-2-5-realtime".
Capabilities
About StepAudio 2.5 Realtime
StepAudio 2.5 Realtime is StepFun's end-to-end real-time conversational voice model. It handles speech input and produces speech output through a single unified architecture with no intermediate ASR/TTS pipeline steps. Key capabilities include persona-consistent roleplay via dedicated RLHF training on million-scale persona data, paralinguistic comprehension (detecting and responding to tone, emotion, and speaking rate), and low-latency dialogue. Supports Chinese and English. Available via WebSocket API (step-2.5-realtime). Analogous in function to OpenAI's GPT Realtime models.