Prepare audio for speech-to-text

Turn any recording or video into the 16 kHz mono 16-bit WAV that Whisper and other speech-to-text models expect.

Input

Choose a file or drop it here

Up to 100 MB.

The recording, or a video with speech in it.
Bring the speech to an even, clear loudness.
Cut away silence at the start and the end.
How quiet counts as silence, in dB below full volume. -40 suits most recordings; use -30 for a noisy room. Used when trimming silence.

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-to-stt-wav \
  -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-to-stt-wav", 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-to-stt-wav`, {
  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-to-stt-wav",
  "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-to-stt-wav. Over MCP: run_tool with slug: "audio-to-stt-wav". Machine-readable: input schema, Markdown. Connect an agent.

Inputs

NameTypeRequiredWhat it does
file file yes The recording, or a video with speech in it. In the API: a file reference such as DROP_ID/f1. Accepts: audio, video.
normalize boolean no Bring the speech to an even, clear loudness. Default: false.
trim_silence boolean no Cut away silence at the start and the end. Default: false.
threshold number no How quiet counts as silence, in dB below full volume. -40 suits most recordings; use -30 for a noisy room. Used when trimming silence. Default: -40. From -90 to -10.

Examples

MP3 to 16 kHz mono WAV

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

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

Speech from a video, levelled and trimmed

Input
{
  "file": "sample.mp4",
  "normalize": true,
  "trim_silence": true
}
Result

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

Questions

Why 16 kHz mono?
Most speech models were trained on 16 kHz mono sound and convert everything to it anyway. Sending it ready-made avoids surprises and keeps uploads small: about 1.9 MB per minute.
My file is over the upload limit of the speech service. What now?
Split it with the split on silence tool, then prepare each part. The result tells you whether the file is under 25 MB, a common limit.