Voice Cleaner

Voice Cleaner is for spoken audio that was recorded in the wrong place: a kitchen, a hotel room, a street corner. It reduces the noise around the voice and hands back a cleaner file. Kadraris runs it at a moderate setting (level 1 of 2), chosen so the voice keeps its natural sound rather than turning metallic.

What you can make

• Podcast episodes recorded at home instead of a studio.
• Voiceovers captured on a laptop microphone.
• Interviews and field recordings, tidied up before transcription or dubbing.
• Lecture and webinar recordings that are easier to listen to.

Settings that matter

• Input: a public audio URL in audio_url.
• Strength: fixed at moderate. Choosing the level, dereverb and the output format is not available in Kadraris yet.
• Billing basis: per started minute, so cut empty stretches at the start and end.
• What to send: the raw recording, not a file that was already compressed or denoised by another app.
• Limits of cleanup: it can remove noise, but it cannot rebuild a voice that was recorded far from the microphone.

Example job

input: audio_url = https://example.com/interview-raw.wav
result: same speech, quieter background

Run a one-minute excerpt first, listen, and only then send the full file.

Questions

What does Voice Cleaner charge?

$0.50 per minute. You see the estimated cost before the job starts, and failed jobs cost nothing.

My room has a strong echo. Will this fix it?

Not directly. Echo needs a dereverb pass, which the engine has but Kadraris does not offer yet, so the tool targets noise only.

Can I clean a song with it?

It is made for speech. For music, use Vocal Remover or Music Extractor; the noise removal guide has more on cleaning voice recordings.

Voice Cleaner in your code

curl https://kadraris.com/v1/generate?wait=60 \
  -H "Authorization: Bearer $KADRARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "voice-cleaner",
  "input": {
    "audio_url": "https://example.com/input.mp3"
  }
}'

import os, time, requests

API = "https://kadraris.com/v1"
H = {"Authorization": f"Bearer {os.environ['KADRARIS_API_KEY']}"}

task = requests.post(f"{API}/generate", headers=H, json={
    "model": "voice-cleaner",
    "input": {
        "audio_url": "https://example.com/input.mp3"
    }
}).json()
while task["status"] in ("queued", "running"):
    time.sleep(3)
    task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()

print(task["status"], task["cost"], [o["url"] for o in task["output"]])

const API = "https://kadraris.com/v1";
const headers = { Authorization: `Bearer ${process.env.KADRARIS_API_KEY}`, "Content-Type": "application/json" };

let task = await (await fetch(`${API}/generate`, {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "voice-cleaner",
    "input": {
      "audio_url": "https://example.com/input.mp3"
    }
  }),
})).json();

while (task.status === "queued" || task.status === "running") {
  await new Promise((r) => setTimeout(r, 3000));
  task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));

Input fields

Fetch this list as JSON with GET /v1/models/voice-cleaner.