Audio Generation Models
Available models for generating audio.
Audio Generation Models
Text-to-Speech
Convert text to natural speech.
bash
curl -X POST \
-H "Authorization: Bearer bnn_live_xxx" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Hello, I am a banana!",
"voice": "alloy"
}
}' \
"https://banan0.com/api/v1/models/fal-ai/tts/run"Music Generation
Generate music from text descriptions.
Cost: ~10-20 tokens per generation
Common Parameters
| Parameter | Type | Description |
|---|---|---|
text | string | Text to speak |
voice | string | Voice preset |
speed | number | Speech speed |