DigitalOcean

Stable Audio 2.5 (Text-to-Audio)

Name: Stable Audio 2.5 (Text-to-Audio)
Brand: DigitalOcean

Canonical ID: digitalocean/fal-ai/stable-audio-25/text-to-audio

More DigitalOcean models More text-to-audio family models

Speech generation model for controllable voice, narration, and audio delivery

Reasoning: No Tool use: No

Overview

text audio

Provider: DigitalOcean
Family: text-to-audio
Release date: 2025-10-08
Last updated: 2026-04-16
Input modalities: text
Output modalities: audio

Pricing and Limits

Token pricing

Input: N/A
Output: N/A
Cached input: N/A

Context and output

Context window: 0
Max output tokens: 0
Qualified ID: digitalocean/fal-ai/stable-audio-25/text-to-audio

Model Summary

Stable Audio 2.5 (Text-to-Audio) is a model listing in the DigitalOcean provider catalog. It is categorized under the text-to-audio family.

The model supports text, audio modalities across input/output paths. Reported context capacity is 0.

Stable Audio 2.5 (Text-to-Audio)

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From DigitalOcean

All-MiniLM-L6-v2

Anthropic Claude 4.1 Opus

Anthropic Claude 4.5 Sonnet

Anthropic Claude 5.5 Haiku

Anthropic Claude Fable 5

Anthropic Claude Fable 5.1

Anthropic Claude Haiku 4.5

Anthropic Claude Opus 4.5