elevenlabs/sound-generation
ElevenLabs sound effects. Turns a written description into a sound effect of up to 30 seconds — footsteps, weather, impacts, UI stings.
Model Inputs
A description of the sound effect to generate, e.g. 'footsteps on gravel, then a metal door creaking open'. At most 450 characters
Length of the effect in seconds. Leave it empty to let the model choose the natural length for the description
How literally to follow the description. Lower is more creative, higher sticks to exactly what was asked for
Audio container, as codec_samplerate_bitrate. mp3 plays everywhere; opus is smaller at the same quality
Result
Pricing
elevenlabs/
sound-generation
Pricing for Synexa AI models works differently from other providers. Instead of being billed by time, you are billed by input and output, making pricing more predictable.
For example, generating 100 requests costs about $5.00.
Check out our docs for more information about how per-request pricing works on Synexa.
| Provider | Price ($) | Saving (%) |
|---|---|---|
| Synexa | $0.05 | - |
| fal | $0.06 | 16.7% |
Readme
ElevenLabs Sound Effects
Describe a sound and get it back as audio: "footsteps on wet gravel, then a heavy iron door creaking open".
text— the description, up to 450 characters.duration_seconds— 0.5 to 30. Leave it empty and the model picks the length that suits the description.prompt_influence— 0 follows the description loosely and invents more, 1 sticks to exactly what was asked for. Default 0.3.output_format— mp3 (plays everywhere) or opus (smaller at the same quality).
One request returns one effect. A five-second effect takes about three seconds to generate.