stable-audio-2.5

Tier 8: 22,667 points · rate: Generation

Comparison method and assumptions.

Pricing

Website Pricing

Type	Cost
Generation	22667 ($0.69) points

All parsed rates (both currencies):

Service	Currency	Amount	Per
Generation	USD	0.69	1 generation
Generation	POINTS	22667	1 generation

Last Checked: 2026-10-22 13:30:30.077805

Bot Information

Creator: @empiriolabsai

Description: Stable Audio 2.5 generates high-quality audio up to 3 minutes long from text prompts, supporting text-to-audio, audio-to-audio transformations, and inpainting with customizable settings like duration, steps, CFG scale, and more. It is Ideal for music production, cinematic sound design, and remixing.

Note: Audio-to-audio and inpaint modes require a prompt alongside an uploaded audio file for generation.

Parameter controls available: 1. Basic - Generation Mode: Text to Audio, Audio to Audio (Transform), Audio Inpaint (Edit Segment) - Output format: WAV (high quality), MP3 (Compressed)

1. Timing and Randomness
2. Duration [1-190 seconds] controls how long generated audio is

3. Seed [0-4294967294]' disables random seed generation. Use random seed must be toggled off to set.

4. Advanced

5. Cfg scale [1-25]: Higher = closer to prompt (recommended 7-15)

6. Steps [4-8]`: Higher = better quality (recommended 6-8)

7. Transformation control (only for audio-to-audio)

8. Strength [0-1]`: How much to change/transform (0.3-0.7 typical)

9. Inpainting control (only for audio-inpaint)

10. Mask start time [seconds] start time of the uploaded audio to modify
11. Mask end time [seconds] end time of the uploaded audio to modify

Extra: Powered by a server managed by @empiriolabsai. Learn more

Architecture

Input Modalities: text, audio

Output Modalities: audio

Modality: text,audio->audio

Technical Details

Model ID: stable-audio-2.5

Object Type: model

Created: 1756869275249

Owned By: EmpirioLabs AI

Root: stable-audio-2.5

API Last Updated: 2026-10-22 13:58:59.076001