---
name: Stable Audio 2.5 (Text-To-Audio)
slug: stable-audio-2-5-text-to-audio
type: Multimodal
providers:
  - digitalocean
description: 'Speech generation model for controllable voice, narration, and audio delivery'
tags:
  - multimodal
is_open_source: false
release_date: '2025-10-08'
capabilities:
  audio: false
  vision: false
  tool_use: false
  citations: false
  reasoning: false
---
Stable Audio 2.5 (Text-To-Audio) is a Multimodal model.
Speech generation model for controllable voice, narration, and audio delivery