← All models
Generates sound effects from text prompts with control over duration, negative prompts, sample count, and output audio format.
Details
- Accepts
- text
Pricing
- Price
- 1.25 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Seed of the first sample; -1 or unset is random |
| promptrequired | string | What the sound effect should sound like |
| duration | number | Seconds of sound to generate, up to the deployment's text-to-SFX maximum |
| num_samples | integer | Number of samples to generate, in one batched forward |
| negative_prompt | — | Sounds to keep out of the result |
| upload_audio_format | stringenum: wav, mp3, aac, flac | Audio format to return |
| upload_audio_bitrate_kbps | — | Bitrate in kbps for an mp3 or aac upload. mp3 is written at exactly this constant rate, one of 32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, 320. aac takes 32 to 256 as a target the encoder may undershoot on mono or sparse audio. Unset keeps the default: mp3 at LAME V0 VBR, aac at a 256 … |
Output
| Field | Type | Description |
|---|---|---|
| audio | array | The generated sound effects, one per sample |
| model | string | |
| seeds | array | Each sample's seed, in the same order |