Mirelo SFX1.6 Text to Audio is a fast AI audio generation model that creates sound effects and ambient audio directly from text prompts, with optional seamless ambience looping. Ready-to-use REST inference API for sound effect generation, game audio, video production, cinematic sound design, background ambience, loopable audio assets, and professional audio workflows with simple integration, no coldstarts, and affordable pricing.
Idle
$0.01per run·~100 / $1
Mirelo AI SFX 1.6 Text-to-Audio generates sound effects, ambience, and short audio clips from natural-language prompts. It supports loop-friendly ambience mode, multiple variations, flexible duration control, and optional doubled loop output for seamless background audio workflows.
Prompt-based audio generation Generate sound effects or ambient audio directly from a text description.
Flexible duration control Choose the target duration for the generated clip, from short effects to longer ambient beds.
Loop-friendly ambience mode
Enable ambience to generate audio designed for seamless looping.
Multiple variations
Generate up to 4 different versions in one request with num_samples.
Optional doubled loop output
When using ambience mode, enable double_output to concatenate the loop with itself for a longer seamless result.
Production-ready API Useful for games, film, podcasts, background ambience, sound design, and content production workflows.
| Parameter | Required | Description |
|---|---|---|
| text_prompt | Yes | Text prompt describing the sound effect or ambient audio to generate. Minimum length: 4 characters. |
| duration | No | Target duration in seconds. Range: 0.1–60. Default: 10. |
| ambience | No | When true, generate and stitch the result so the tile loops seamlessly. Default: false. |
| double_output | No | Only used when ambience is true: concatenate the loop with itself for a 2x-length output. Default: false. |
| num_samples | No | Number of variations to generate. Range: 1–4. Default: 1. |
1 to 4.Dark cinematic ambience with distant thunder, soft low-frequency rumble, subtle wind, and evolving tension
Pricing is based on generated duration and number of samples.
| Duration | 1 Sample | 2 Samples | 3 Samples | 4 Samples |
|---|---|---|---|---|
| 1s | $0.01 | $0.02 | $0.03 | $0.04 |
| 5s | $0.05 | $0.10 | $0.15 | $0.20 |
| 10s | $0.10 | $0.20 | $0.30 | $0.40 |
| 20s | $0.20 | $0.40 | $0.60 | $0.80 |
| 30s | $0.30 | $0.60 | $0.90 | $1.20 |
| 60s | $0.60 | $1.20 | $1.80 | $2.40 |
text_prompt does not affect pricingambience and double_output do not change billing unless your backend explicitly makes them billableambience when the output needs to loop smoothly.double_output only when you want a longer looped deliverable.num_samples when you want multiple creative options from the same prompt.text_prompt is required.duration supports 0.1–60 seconds.num_samples supports 1–4.double_output only applies when ambience is enabled.