Split audio on silence

Cut a recording into separate files at its pauses, for example one file per track, sentence or speaker turn.

Input

Choose a file or drop it here

Up to 100 MB.

The audio file.
How quiet counts as silence, in dB below full volume. -40 suits most recordings; use -30 for a noisy room.
Shortest pause that counts as a place to cut, in seconds.
Shortest part to make, in seconds. Shorter pieces stay joined to the next one.
Most parts to make. With more pauses than this, the longest pauses are used.
Seconds of the pause to keep at each side of a cut.
Format of the result: mp3, wav, ogg, opus, flac or m4a. Leave empty to keep the format of the upload.

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.

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-split-on-silence \
  -H 'Content-Type: application/json' \
  -d '{"input":{"file":"DROP_ID/f1"},"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")}, "wait": 30}
reply = call("POST", "/v1/tools/audio-split-on-silence", 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-split-on-silence`, {
  method: "POST",
  headers: {"Content-Type": "application/json"},
  body: JSON.stringify({input: {"file":await upload(file, "sample.mp3")}, 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-split-on-silence",
  "input": {
    "file": "DROP_ID/f1"
  }
}

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"
  },
  "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-split-on-silence. Over MCP: run_tool with slug: "audio-split-on-silence". Machine-readable: input schema, Markdown. Connect an agent.

Inputs

NameTypeRequiredWhat it does
file file yes The audio file. In the API: a file reference such as DROP_ID/f1. Accepts: audio.
threshold number no How quiet counts as silence, in dB below full volume. -40 suits most recordings; use -30 for a noisy room. Default: -40. From -90 to -10.
min_silence number no Shortest pause that counts as a place to cut, in seconds. Default: 0.5. From 0.05 to 60.
min_part number no Shortest part to make, in seconds. Shorter pieces stay joined to the next one. Default: 1. From 0 to 3600.
max_parts integer no Most parts to make. With more pauses than this, the longest pauses are used. Default: 20. From 2 to 50.
padding number no Seconds of the pause to keep at each side of a cut. Default: 0.1. From 0 to 5.
format string no Format of the result: mp3, wav, ogg, opus, flac or m4a. Leave empty to keep the format of the upload. One of: mp3, wav, ogg, opus, flac, m4a.

Examples

Two tones with a pause become two files

Input
{
  "file": "sample.mp3"
}
Result

Press the example button above to run it on the sample file.

A recording with no pause is left whole

Input
{
  "file": "sample.wav"
}
Result

Press the example button above to run it on the sample file.

Questions

What happens to the silence?
Silence at the very start and end is dropped. Each pause used as a cut is removed apart from the padding kept on each side. Pauses not used as cuts stay inside their part.
What if no silence is found?
No files are made and the result says so. Raise the threshold, for example to -30, or shorten the minimum pause.
How many parts can I get?
Up to 50. When a recording has more pauses than the limit you set, the longest pauses are used as the cuts.