Split audio on silence
Cut a recording into separate files at its pauses, for example one file per track, sentence or speaker turn.
Input
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
| Name | Type | Required | What 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
{
"file": "sample.mp3"
}Press the example button above to run it on the sample file.
A recording with no pause is left whole
{
"file": "sample.wav"
}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.
Related tools
- Find silence in audioList every silent stretch in a recording with its start, end and length, and total up silence and sound.
audio-silence-detect - Trim silence from audioRemove the silence at the start and end of a recording, leaving the pauses in the middle untouched.
audio-silence-trim - Trim audioCut a section out of an audio file by start and end time, with optional fade in and fade out.
audio-trim - Join audio filesJoin 2 to 20 audio files end to end into one, in the order given, with an optional gap or crossfade between them.
audio-concat - Prepare audio for speech-to-textTurn any recording or video into the 16 kHz mono 16-bit WAV that Whisper and other speech-to-text models expect.
audio-to-stt-wav - Audio file infoShow the format, length, bitrate, codec, sample rate, channels and tags of an audio file, plus its peak and average volume.
audio-info