Convert MP3 to Opus

Upload a recording in MP3 format and download it as Opus. Free, no signup, files up to 100 MB. You see live progress while it runs, and the same conversion is available as an API call and to AI agents over MCP.

Input

Choose a file or drop it here

Up to 100 MB.

The audio file, or a video whose sound you want.
Format of the result.
Bitrate in kbit/s for mp3, ogg, opus and m4a. Higher sounds better and is larger. Leave empty for a sensible default.
Sample rate of the result in Hz. Leave empty to keep the original.
Mono or stereo. Leave empty to keep the original.

Result

Choose a file and press Run.

Files you upload and the results are stored for one hour, then deleted. Anyone who has the link can open them, so don't upload anything private.

How to convert MP3 to Opus

  1. Choose your MP3 file, or drop it onto the page.
  2. Adjust the settings if you want to. The defaults suit most files.
  3. Press Run and watch the progress bar.
  4. Download the Opus file, or copy its link to share it.

This page runs the convert audio tool with format set to opus. Open the tool itself for every option.

What happens in this conversion

Quality
Both MP3 and Opus discard some sound to stay small, so converting between them loses a little more each time. Use a bitrate at least as high as the original, and convert from the original recording when you have it.
Bitrate
Opus needs far fewer bits than MP3: 24 to 32 kbit/s is clear for speech and 96 kbit/s is transparent for most music.
Tags
Title, artist and album tags are carried over where the new format can store them.

MP3 and Opus compared

FormatWhat it isBest forWatch out for
MP3
MP3 audio
MP3 is the audio format everything plays: phones, cars, browsers, podcast apps and thirty years of music players.Music and speech that must play on any device.It discards some sound to stay small, and newer formats sound better at the same size.
Opus
Opus audio
Opus is the most efficient common audio format: clear speech at very low bitrates. Voice messages and video calls use it.Voice recordings and streaming at small sizes.Older players and some editing programs cannot open it.

Use it from code or an agent

# 1. Upload the file. The reply ends with a line "ref  <id>/f1": that is the file reference.
curl -T sample.mp3 https://setget.net/drop/

# 2. Run the tool with that reference. "wait" holds the reply for up to 30 seconds while the job runs.
curl -s https://setget.net/v1/tools/audio-convert \
  -H 'Content-Type: application/json' \
  -d '{"input":{"file":"DROP_ID/f1","format":"opus"},"wait":30}'

# 3. The reply is {"tool", "ms", "result", "files": [{"name", "size", "url", "ref"}], "job"}.
#    Download a result file from its "url", or pass its "ref" to another tool.
#    Still running after the wait? The reply is 202 with "job": follow it with
#    curl -s https://setget.net/v1/jobs/JOB_ID?wait=30
import json, urllib.parse, urllib.request

BASE = "https://setget.net"

def call(method, path, body=None, headers=None):
    request = urllib.request.Request(BASE + path, body, headers or {}, method=method)
    return json.load(urllib.request.urlopen(request))

def upload(path):
    """Step 1: upload a file and get its reference."""
    name = path.replace("\\", "/").rsplit("/", 1)[-1]
    with open(path, "rb") as handle:
        reply = call("PUT", "/drop/" + urllib.parse.quote(name), handle.read(), {"Accept": "application/json"})
    return reply["file"]["ref"]

# Step 2: run the tool with the reference.
body = {"input": {'file': upload("sample.mp3"), 'format': 'opus'}, "wait": 30}
reply = call("POST", "/v1/tools/audio-convert", json.dumps(body).encode(), {"Content-Type": "application/json"})

# Step 3: a job that is still running comes back as {"job": ...}. Wait for it.
while "result" not in reply and reply.get("job", reply).get("status") in ("queued", "running"):
    reply = call("GET", "/v1/jobs/" + reply.get("job", reply)["id"] + "?wait=30")
if "error" in reply:
    raise SystemExit(reply["error"]["message"])
print(reply["result"])
for file in reply["files"]:   # result files: download from "url", or pass "ref" to another tool
    print(file["name"], file["size"], file["url"], file["ref"])
const BASE = "https://setget.net";

// Step 1: upload a file and get its reference. file: a File or Blob
// (in Node: new Blob([fs.readFileSync(path)])).
async function upload(file, name) {
  const response = await fetch(`${BASE}/drop/${encodeURIComponent(name)}`, {
    method: "PUT", headers: {Accept: "application/json"}, body: file,
  });
  return (await response.json()).file.ref;
}

// Step 2: run the tool with the reference.
let reply = await (await fetch(`${BASE}/v1/tools/audio-convert`, {
  method: "POST",
  headers: {"Content-Type": "application/json"},
  body: JSON.stringify({input: {"file":await upload(file, "sample.mp3"),"format":"opus"}, wait: 30}),
})).json();

// Step 3: a job that is still running comes back as {job}. Wait for it.
while (!reply.result && ["queued", "running"].includes((reply.job || reply).status)) {
  reply = await (await fetch(`${BASE}/v1/jobs/${(reply.job || reply).id}?wait=30`)).json();
}
if (reply.error) throw new Error(reply.error.message);
console.log(reply.result);
for (const file of reply.files) console.log(file.name, file.size, file.url, file.ref);
1. Upload. Tool: drop
Arguments:
{
  "action": "create",
  "files": [
    {
      "name": "sample.mp3",
      "size": "<bytes>"
    }
  ]
}
PUT each file's bytes to its "upload.url" with the listed headers, and keep its "ref".
With a shell, one command does both: curl -T FILE https://setget.net/drop/

2. Run. Tool: run_tool
Arguments:
{
  "slug": "audio-convert",
  "input": {
    "file": "DROP_ID/f1",
    "format": "opus"
  }
}

3. The answer holds "result" and "files" (each with "url" and "ref").
If it holds a "job" that is still running instead, follow it. Tool: job
Arguments:
{
  "action": "wait",
  "id": "JOB_ID"
}
{
  "input": {
    "file": "DROP_ID/f1",
    "format": "opus"
  },
  "wait": 30
}

This is a file tool, so a call takes three steps: upload the file to get a reference, run the tool with that reference, then read the result and download its files. Uploads and results are public by link and expire after one hour.

Endpoint: POST /v1/tools/audio-convert. Over MCP: run_tool with slug: "audio-convert". Machine-readable: input schema, Markdown. Connect an agent.

Inputs

NameTypeRequiredWhat it does
file file yes The audio file, or a video whose sound you want. In the API: a file reference such as DROP_ID/f1. Accepts: audio, video.
format string no Format of the result. One of: mp3, wav, ogg, opus, flac, m4a. Default: "opus".
bitrate integer no Bitrate in kbit/s for mp3, ogg, opus and m4a. Higher sounds better and is larger. Leave empty for a sensible default. One of: 32, 48, 64, 96, 128, 160, 192, 256, 320.
sample_rate integer no Sample rate of the result in Hz. Leave empty to keep the original. One of: 8000, 11025, 12000, 16000, 22050, 24000, 32000, 44100, 48000, 96000.
channels string no Mono or stereo. Leave empty to keep the original. One of: mono, stereo.

Questions

Is it free to convert MP3 to Opus?
Yes. There is no signup, no watermark and no paid tier. A fair-use limit per day applies to keep the service available to everyone.
How large can the MP3 file be?
Up to 100 MB.
What happens to my file?
It is stored for one hour so you can download the result, then deleted. Anyone who has the link can open it during that hour, so do not upload anything private.
Can a script or an AI agent convert MP3 to Opus?
Yes. Call POST https://setget.net/v1/tools/audio-convert with JSON, or use the run_tool tool of the SetGet MCP server with slug "audio-convert". The code samples on this page are ready to copy.

More conversions