---
name: Stepaudio 2.5 Tts
slug: stepaudio-2-5-tts
type: Multimodal
providers:
  - stepfun
description: 'Speech generation model for controllable voice, narration, and audio delivery'
tags:
  - step
  - multimodal
is_open_source: false
release_date: '2026-04-16'
capabilities:
  audio: false
  vision: false
  tool_use: false
  citations: false
  reasoning: false
---
Stepaudio 2.5 Tts is a Multimodal model.
Speech generation model for controllable voice, narration, and audio delivery