Skip to main content
POST
Audio Sound Effects
Synchronous endpoint. Describe a sound — door slam, rain, sword unsheathing, ambient room — get back a clip. Pairs naturally with /v1/audio/music for video and game soundtracking.

Request

application/json body.
model
string
default:"elevenlabs-sfx"
SFX model. Currently only elevenlabs-sfx is shipped.
prompt
string
required
Description of the sound. Max 500 characters. Also accepts text as an alias.
duration_seconds
number
Optional duration 0.5 to 22 seconds. Omit to let the model auto-pick a sensible length.
prompt_influence
number
default:"0.3"
How literal the prompt should be (0 = creative, 1 = strict). Range 01.
response_format
string
default:"mp3_44100_128"
Audio format. Same options as audio/speech.
save_to_blob
string
Optional query param. Set to 1 to have Kyma upload the resulting MP3 to Vercel Blob, write a multimodal_jobs row, and return JSON { job_id, kind: "audio", url, duration_sec, cost_usd, balance_usd } instead of streaming bytes. Used by Canvas and Muse audio kinds — most direct API callers don’t need this.

Response

Default (streaming)

200 OK with audio bytes. Flat pricing — duration doesn’t change the cost.

With ?save_to_blob=1

200 OK with JSON:

Errors

See also