Stable Audio 2.5 (Text-to-Audio) API
About
Stable Audio 2.5 (Text-to-Audio) is a high-performance LLM available via the DigitalOcean API, ideal for scalable text generation and natural language processing. This model delivers available completely free of charge. Access Stable Audio 2.5 (Text-to-Audio) via the DigitalOcean API with reliable low-latency inference.
Capabilities
Input Modalities
text
Output Modalities
audio
Reasoning
No
Structured Output
No
Tool Use
No
WeightsClosed
Limits
Context Window
N/A
Tokens
Input Limit
N/A
Tokens
Max Output
N/A
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
Stable Audio 2.5 (Text-to-Audio) by DigitalOcean costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
ID
fal-ai/stable-audio-25/text-to-audio
Provider
DigitalOceanFamily
Release Date
Oct 8, 2025
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
DIGITALOCEAN_ACCESS_TOKEN
API Base URL
https://inference.do-ai.run/v1