Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/AssemblyAI/realtime-transcription-browser-js-example/llms.txt

Use this file to discover all available pages before exploring further.

​
GET /token

Generates a temporary authentication token for AssemblyAI’s real-time transcription service.

​
Request

GET /token HTTP/1.1
Host: localhost:8000
No request parameters are required.

​
Response

​
token
string
A temporary authentication token valid for 60 seconds. This token is used to establish a WebSocket connection with AssemblyAI’s streaming service.
Success Response (200 OK) 
{
  "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."
}

​
Error Handling

Error Response (500 Internal Server Error) 
{
  "error": "Failed to generate token"
}
This error occurs when:
  • The AssemblyAI API key is invalid or missing
  • The token generation service is unavailable
  • Network connectivity issues prevent token generation

​
Implementation Details

The endpoint is defined in server.js:10-17 and internally calls the generateTempToken() function with a 60-second expiration time (the maximum allowed value is 600 seconds). 
app.get("/token", async (req, res) => {
  try {
    const token = await generateTempToken(60); // Max value 600
    res.json({ token });
  } catch (error) {
    res.status(500).json({ error: "Failed to generate token" });
  }
});

​
Usage Example

const response = await fetch("http://localhost:8000/token");
const data = await response.json();

if (data.error || !data.token) {
  alert("Failed to get temp token");
  return;
}

const endpoint = `wss://streaming.assemblyai.com/v3/ws?sample_rate=16000&formatted_finals=true&token=${data.token}`;
const ws = new WebSocket(endpoint);
See the complete implementation in public/index.js:83-90.

Build docs developers (and LLMs) love

Get started for freeTalk to us