Skip to content
Log inGet an API key
Newzilapi/nr-4.1 is live

One API key for every InverseAI model.

Prepaid credit, per-second billing and a plain async job API. Start with studio-grade noise reduction at $0.033 per audio minute.

  • Top up from $10
  • Credit valid 12 months
  • Billed per second
# 1. Upload: start, PUT the bytes to the signed URL, finish
curl https://api.zilapi.com/v1/files \
  -H "Authorization: Bearer $ZILAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"filename": "episode-142.wav", "size_bytes": 18432000,
       "content_type": "audio/wav"}'
# PUT to upload.url with every header listed in upload.headers
curl -X PUT "$UPLOAD_URL" -H "Content-Type: audio/wav" \
  --data-binary @episode-142.wav
curl -X POST https://api.zilapi.com/v1/files/$FILE_ID/complete \
  -H "Authorization: Bearer $ZILAPI_KEY"

# 2. When the file is ready, start a denoise job
curl https://api.zilapi.com/v1/audio/denoise \
  -H "Authorization: Bearer $ZILAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"file": "file_3Lm8QpZ2rT6w", "model": "zilapi/nr-4.1"}'

# 3. Poll the job, then fetch a download URL for the MP3
curl https://api.zilapi.com/v1/jobs/job_7Hq2xV9mKp4R \
  -H "Authorization: Bearer $ZILAPI_KEY"
curl https://api.zilapi.com/v1/jobs/job_7Hq2xV9mKp4R/output \
  -H "Authorization: Bearer $ZILAPI_KEY"
200 OK · GET /v1/jobs/job_7Hq2xV9mKp4R
{
  "id": "job_7Hq2xV9mKp4R",
  "object": "job",
  "task": "audio.denoise",
  "model": "zilapi/nr-4.1",
  "status": "succeeded",
  "input": { "file": "file_3Lm8QpZ2rT6w", "duration_seconds": 191.4 },
  "output": { "format": "mp3", "bitrate_kbps": 192, "size_bytes": 4608000 },
  "cost": { "charged_micros": 105600, "display": "$0.1056" },
  "mode": "live"
}
Models

One model today. More on the same key.

All models
Audio · DenoiseAvailable

zilapi/nr-4.1

Noise reduction 4.1

Removes background noise, hum and room tone from speech and music while keeping the voice natural.

$0.033/ audio min
Common audio in≤ 6 h≤ 5 GB→ MP3 192 kbps
Audio · SeparationComing soon

zilapi/vms-1

Vocal and music separation

Splits a song or mix into a vocal track and an accompaniment track.

Same key, same credit
ImageComing soon

Image tools

InverseAI image models

Background removal and upscaling from InverseAI's image apps, billed per image.

Same key, same credit
How it works

Three calls, no SDK required.

  1. 01

    Upload the file

    Any common audio format, up to 6 h or 5 GB. You get a file id and a signed URL to PUT the bytes to.

    POST /v1/files
  2. 02

    Create a job

    Name the model and the file. The job starts queued and runs on our GPUs.

    POST /v1/audio/denoise
  3. 03

    Poll, then download

    When the status is succeeded, fetch the MP3. The job shows exactly what you paid.

    GET /v1/jobs/{id}
Pricing

Pay for the audio you process. Nothing else.

No subscription and no seats. Add credit from $10 with a card through Stripe; jobs draw it down by the second. Failed and canceled jobs cost nothing. There is no free trial; test keys are free.

Open the price calculator
zilapi/nr-4.1
Noise reduction
Billed per second · 1-minute minimum · up to 6 h / 5 GB per file
$0.033/ audio min
What example files cost
Your fileBillableYou pay
Voicemail, 0 m 45 s60 s (minimum)$0.0330
Podcast clip, 3 m 12 s192 s$0.1056
Lecture, 48 m 30 s2,910 s$1.6005
Longest file, 6 h21,600 s$11.8800
Trust and security

Built for the people who pay the bill.

Get a key in two minutes.

Sign up with email, Google or GitHub. Test keys are free; live jobs start after your first $10.