StepAudio 2.5 Realtime

StepAudio 2.5 Realtime is an end-to-end speech-to-speech model served over a WebSocket Realtime API. It takes streaming audio or text and responds with streaming audio and a matching text transcript,…

stepFun/stepaudio-2.5-realtime

StepAudio 2.5 Realtime is an end-to-end speech-to-speech model served over a WebSocket Realtime API. It takes streaming audio or text and responds with streaming audio and a matching text transcript, with no separate speech-to-text or text-to-speech stage in between. It understands both the words and the tone behind them, such as hesitation, a slight laugh, or frustration, and replies with natural, expressive speech in real time.

Specifications & capabilities

Input
audio, text
Output
speech, text
Supported voices
elegantgentle-female, lively-girl, livelybreezy-female, magnetic-voiced-male, soft-spoken-gentleman, vibrant-youth, zixinnansheng
Published model ID
stepaudio-2.5-realtime
Capabilities
audioInput, multimodal, speechOutput, streaming

Provider specifications & access

1–1 / 1

StepAudio 2.5 Realtime ↗

source model id
stepaudio-2.5-realtime
hosting
stepfun-global-hosted
platforms
  • StepFun
architecture
input_modalities
  • audio
  • text
output_modalities
  • speech
  • text
capabilities
  • audioInput
  • multimodal
  • speechOutput
  • streaming

Original sources

1–2 / 2

StepFun · Model documentation ↗

StepFun · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace