Xound API · Early access

Studio-grade audio enhancement,
in one API call.

Add AI noise removal and speech restoration to your app, pipeline, or product. Upload audio or video, get back clean, broadcast-ready sound. Pay per minute — no infrastructure to run.

Read the docs

Same engine that powers xound.io · Processed on our servers · Files auto-deleted after 3 days

Two endpoints. That's it.

Send a file, poll the job, download the result. No SDK required — it's just HTTP.

✓ Two engines: classic (noise removal, keeps the original voice & stereo) or studio (speech restoration) — choose per request
✓ Output as MP3 or uncompressed 24-bit / 48 kHz WAV for studio pipelines
✓ Audio and video in, clean media out
✓ Loudness normalization for Spotify / YouTube targets
✓ Duration preserved sample-accurately — lip-sync safe

curl https://api.xound.io/v1/enhance \
  -H "Authorization: Bearer $XOUND_API_KEY" \
  -F "file=@input.wav" \
  -F "enhancer=classic" \
  -F "format=wav"        # mp3 (default) or 24-bit/48kHz wav

# → { "job_id": "…", "status": "processing",
#     "status_url": "…", "result_url": "…" }

Pricing that scales with you

Billed per processed audio-minute. Monthly plans include minutes; overage is metered — no hard walls.

Starter

$29/mo

1,500 min / mo

then $0.03/min

Indie apps & MVPs

Growth

$99/mo

6,000 min / mo

then $0.02/min

Content pipelines & agencies

Scale

$399/mo

30,000 min / mo

then $0.015/min

High-volume products

Enterprise

Custom

Volume pricing

SLA & dedicated

Talk to us

Undercuts comparable enhancement APIs while keeping restoration quality. Global USD pricing.

How it works

Get a key

Request early access — we issue you an API key.

POST your file

Call /v1/enhance with the audio or video.

Download clean media

Poll the job, fetch the enhanced result.