Transcribe a short audio file

Overview

Send an audio file in a single HTTP request, get a transcript back in milliseconds. No polling, no session management.

Python
JavaScript
cURL

import requests

with open("sample.wav", "rb") as f:
    audio = f.read()

response = requests.post(
    "https://sync.assemblyai.com/transcribe",
    headers={
        "Authorization": "<YOUR_API_KEY>",
        "X-AAI-Model": "universal-3-5-pro",
    },
    files={
        "audio": ("sample.wav", audio, "audio/wav"),
    },
    timeout=60,
)
response.raise_for_status()
result = response.json()
print(result["text"])

import { readFileSync } from "fs";

const audio = readFileSync("sample.wav");
const form = new FormData();
form.append("audio", new Blob([audio], { type: "audio/wav" }), "sample.wav");

const response = await fetch("https://sync.assemblyai.com/transcribe", {
  method: "POST",
  headers: {
    Authorization: "<YOUR_API_KEY>",
    "X-AAI-Model": "universal-3-5-pro",
  },
  body: form,
});

if (!response.ok) {
  const error = await response.json();
  throw new Error(error.message || error.detail);
}

const result = await response.json();
console.log(result.text);

curl -X POST https://sync.assemblyai.com/transcribe \
  -H 'Authorization: <YOUR_API_KEY>' \
  -H 'X-AAI-Model: universal-3-5-pro' \
  -F 'audio=@sample.wav;type=audio/wav'

The Sync API uses our flagship Universal-3.5 Pro model and accepts audio from 80 milliseconds up to 120 seconds. It transcribes with state-of-the-art accuracy in 19 languages.

When to use Sync STTSync STT is ideal for pre-recorded audio clips under 2 minutes where you need an immediate response without polling — for example, voice message transcription, short call recordings, or voice agent pipelines that handle turn detection externally and submit completed utterances for transcription. For audio longer than 120 seconds, use Pre-recorded STT. For live microphone audio, use Real-time STT.

Before you begin

To complete this guide, you need:

An AssemblyAI API key — get one by signing up at assemblyai.com
An audio file in WAV format (or raw PCM S16LE)
Python 3.8+, Node.js 18+, or cURL

Step 1: Configure your API key

Browse to API Keys in your dashboard and copy your API key.

Python
JavaScript
cURL

YOUR_API_KEY = "<YOUR_API_KEY>"

const YOUR_API_KEY = "<YOUR_API_KEY>";

Replace <YOUR_API_KEY> in the request header:

-H 'Authorization: <YOUR_API_KEY>'

Step 2: Send the audio file

The Sync API accepts multipart/form-data with an audio part. For WAV files, set the part’s Content-Type to audio/wav. The X-AAI-Model: universal-3-5-pro header is required on every request.

Python
JavaScript
cURL

Install the requests library if you haven’t already:

pip install requests

Send the audio file:

import requests

with open("sample.wav", "rb") as f:
    audio = f.read()

response = requests.post(
    "https://sync.assemblyai.com/transcribe",
    headers={
        "Authorization": "<YOUR_API_KEY>",
        "X-AAI-Model": "universal-3-5-pro",
    },
    files={
        "audio": ("sample.wav", audio, "audio/wav"),
    },
    timeout=60,
)
response.raise_for_status()

import { readFileSync } from "fs";

const audio = readFileSync("sample.wav");
const form = new FormData();
form.append("audio", new Blob([audio], { type: "audio/wav" }), "sample.wav");

const response = await fetch("https://sync.assemblyai.com/transcribe", {
  method: "POST",
  headers: {
    Authorization: "<YOUR_API_KEY>",
    "X-AAI-Model": "universal-3-5-pro",
  },
  body: form,
});

if (!response.ok) {
  const error = await response.json();
  throw new Error(error.message || error.detail);
}

curl -X POST https://sync.assemblyai.com/transcribe \
  -H 'Authorization: <YOUR_API_KEY>' \
  -H 'X-AAI-Model: universal-3-5-pro' \
  -F 'audio=@sample.wav;type=audio/wav'

Sending raw PCM audioIf your audio is raw PCM (S16LE little-endian), set the part Content-Type to audio/pcm and include sample_rate and channels in a config part. See Sending raw PCM audio below for a full example.

Step 3: Parse the response

A successful request returns a JSON object with the transcript and word-level details:

{
  "text": "Hi, I'm calling about my Best Buy order...",
  "words": [
    { "text": "Hi",  "start": 0,   "end": 200, "confidence": 0.91 },
    { "text": "I'm", "start": 220, "end": 320, "confidence": 0.88 }
  ],
  "confidence": 0.87,
  "audio_duration_ms": 101567,
  "session_id": "eb92c4ff-4bbb-429f-9b99-7279d7fe738f"
}

Field	Description
`text`	Full transcript of the audio.
`words`	Word-level timestamps (`start`, `end`, in milliseconds) and per-word `confidence`.
`confidence`	Overall transcript confidence score (0–1).
`audio_duration_ms`	Duration of the submitted audio in milliseconds.
`session_id`	Server-generated UUID. Include this when contacting support.

Python
JavaScript
cURL

result = response.json()
print(result["text"])
print(result["session_id"])

const result = await response.json();
console.log(result.text);
console.log(result.session_id);

The response JSON is printed to stdout. Pipe to jq to extract fields:

curl -X POST https://sync.assemblyai.com/transcribe \
  -H 'Authorization: <YOUR_API_KEY>' \
  -H 'X-AAI-Model: universal-3-5-pro' \
  -F 'audio=@sample.wav;type=audio/wav' \
  | jq '.text'

Sending raw PCM audio

When your audio is raw PCM (S16LE little-endian), set the audio part Content-Type to audio/pcm and include sample_rate and channels in the config part:

Python
JavaScript
cURL

import json
import requests

with open("sample.pcm", "rb") as f:
    audio = f.read()

response = requests.post(
    "https://sync.assemblyai.com/transcribe",
    headers={
        "Authorization": "<YOUR_API_KEY>",
        "X-AAI-Model": "universal-3-5-pro",
    },
    files={
        "audio": ("sample.pcm", audio, "audio/pcm"),
        "config": (
            None,
            json.dumps({"sample_rate": 16000, "channels": 1}),
            "application/json",
        ),
    },
    timeout=60,
)
response.raise_for_status()
print(response.json()["text"])

import { readFileSync } from "fs";

const audio = readFileSync("sample.pcm");
const form = new FormData();
form.append("audio", new Blob([audio], { type: "audio/pcm" }), "sample.pcm");
form.append(
  "config",
  new Blob(
    [JSON.stringify({ sample_rate: 16000, channels: 1 })],
    { type: "application/json" }
  )
);

const response = await fetch("https://sync.assemblyai.com/transcribe", {
  method: "POST",
  headers: {
    Authorization: "<YOUR_API_KEY>",
    "X-AAI-Model": "universal-3-5-pro",
  },
  body: form,
});

const result = await response.json();
console.log(result.text);

curl -X POST https://sync.assemblyai.com/transcribe \
  -H 'Authorization: <YOUR_API_KEY>' \
  -H 'X-AAI-Model: universal-3-5-pro' \
  -F 'audio=@sample.pcm;type=audio/pcm' \
  -F 'config={"sample_rate":16000,"channels":1};type=application/json'

Next steps

Prompting and keyterms — improve accuracy with custom prompts and keyterm biasing
Conversation context — pass prior dialogue for multi-turn continuity
Language selection — transcribe in any of the 19 supported languages
Audio requirements — duration, size, and format constraints
Error handling — status codes and retry guidance
Cloud endpoints & data residency — use the EU endpoint for data residency
API reference — full endpoint documentation

Need help?

If you get stuck, contact our support team at support@assemblyai.com or create a support ticket. Include the session_id from the response to help us look up your request.

​Overview

​Before you begin

​Step 1: Configure your API key

​Step 2: Send the audio file

​Step 3: Parse the response

​Sending raw PCM audio

​Next steps

​Need help?

Overview

Before you begin

Step 1: Configure your API key

Step 2: Send the audio file

Step 3: Parse the response

Sending raw PCM audio

Next steps

Need help?