StepAudio 3 Gen

StepAudio 3 Gen creates comprehensive audio content from natural language. Describe roles, timbre, and emotion, and it generates expressive, controllable voice—then adds sound effects, ambient sound,…

stepFun/stepaudio-3-gen

StepAudio 3 Gen creates comprehensive audio content from natural language. Describe roles, timbre, and emotion, and it generates expressive, controllable voice—then adds sound effects, ambient sound, background music, and singing, orchestrated into a single finished clip. Technical report · More demos · Voice Studio

Specifications & capabilities

Input
text, audio
Output
audio
Published model ID
stepaudio-3-gen
Capabilities
audioInput, audioOutput, multimodal, musicGeneration, speechOutput

Provider specifications & access

1–1 / 1

StepAudio 3 Gen ↗

source model id
stepaudio-3-gen
hosting
stepfun-global-hosted
platforms
  • StepFun
architecture
input_modalities
  • text
  • audio
output_modalities
  • audio
capabilities
  • audioInput
  • audioOutput
  • multimodal
  • musicGeneration
  • speechOutput

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