API docs / Audio models

resemble-enhance API

Enhances audio quality by improving clarity, reducing noise, and restoring degraded audio files. Uses AI-driven enhancement techniques with configurable denoising options and multiple solver algorithms (Midpoint, RK4, Euler) for processing. Outputs both denoised and enhanced versions of the input audio.

Model id
resemble-ai/resemble-enhance
Provider
resemble-ai
Output
Audio
Price
Depends on the options; the same as on voor.ai.

Request

POST https://voor.ai/v1/generations with "model": "resemble-ai/resemble-enhance". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "resemble-ai/resemble-enhance",
  "input": {
    "reference_audios": [
      "https://example.com/input.png"
    ]
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
reference_audiosrequiredarray of URLs

Input audio file

Up to 1 files · Accepts audio/*

denoise_flagboolean

Denoise the audio

Default: false

number_function_evaluationsnumber

CFM Number of function evaluations to use

Default: 64

Min 1 · Max 128

prior_temperaturenumber

CFM Prior temperature to use

Default: 0.5

Min 0 · Max 1

solverstring

Solver to use

Default: Midpoint

One of: Midpoint, RK4, Euler