Generates sound effects from text prompts with control over duration, negative prompts, sample count, and output audio format.
Mirelo SFX2.0 (mirelo-ai/sfx2.0/text-to-audio) is a music model from Mirelo AI. Pricing via AIgateway: $0.010 per second. Call it via https://api.aigateway.sh/v1/audio/music — set model="mirelo-ai/sfx2.0/text-to-audio".
curl https://api.aigateway.sh/v1/audio/music \
-H "Authorization: Bearer $AIGATEWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"mirelo-ai/sfx2.0/text-to-audio","prompt":"lo-fi piano with light rain","duration":15}'{
"model": "mirelo-ai/sfx2.0/text-to-audio",
"prompt": "Calm lo-fi instrumental, warm Rhodes, vinyl crackle",
"is_instrumental": true, // omit and pass "lyrics" for a vocal track
"duration": 15, // seconds — honored, clamped to this model's range
}
// Response is an async job — poll /v1/jobs/<id> until status === "completed".{
"id": "job_abc123",
"status": "queued",
"model": "mirelo-ai/sfx2.0/text-to-audio",
"created": 1776947082
}
// After completion:
{
"id": "job_abc123",
"status": "completed",
"result": {
"url": "https://media.aigateway.sh/music/abc123.mp3",
"duration": 30
}
}import os, requests
r = requests.post(
"https://api.aigateway.sh/v1/audio/music",
headers={"Authorization": f"Bearer {os.environ['AIGATEWAY_API_KEY']}"},
json={
"model": "mirelo-ai/sfx2.0/text-to-audio",
"prompt": "Calm lo-fi instrumental, warm Rhodes, vinyl crackle",
"is_instrumental": True
},
)
print(r.json())