Speech to Text

Transcribe audio to text

POST /stt

cURL

curl -X POST https://api.60db.ai/stt \
  -H "Authorization: Bearer your-api-key" \
  -F "audio=@recording.mp3" \
  -F "language=en" \
  -F "timestamps=true"

import { SixtyDBClient } from "60db";

const client = new SixtyDBClient("your-api-key");

const file = document.querySelector('input[type="file"]').files[0];

const result = await client.speechToText(file, {
  language: "en",
});

console.log("Transcription:", result.text);

from sixtydb import SixtyDBClient

client = SixtyDBClient('your-api-key')

with open('recording.mp3', 'rb') as audio_file:
    result = client.speech_to_text(audio_file, language='en')
    print(f"Transcription: {result['text']}")
    print(f"Confidence: {result['confidence']}")

Response

{
  "text": "Hello, this is a test of the speech to text API. It works great!",
  "language": "en",
  "confidence": 0.95,
  "duration": 5.2,
  "words": [
    {
      "word": "Hello",
      "start": 0.0,
      "end": 0.5,
      "confidence": 0.98
    },
    {
      "word": "this",
      "start": 0.6,
      "end": 0.8,
      "confidence": 0.97
    }
  ]
}

Request

Headers

Authorization · string · required

Bearer token with your API key

Content-Type · string · required

multipart/form-data

Form Data

audio · file · required

Audio file to transcribe - Supported formats: MP3, WAV, FLAC, OGG, M4A - Max file size: 25MB - Max duration: 10 minutes

language · string

Language code for transcription (e.g., “en”, “es”, “fr”). If not specified, language will be auto-detected.

model · string · default: "general"

Transcription model: “general”, “phone_call”, “meeting”, “medical”

timestamps · boolean · default: "false"

Include word-level timestamps in the response

speaker_labels · boolean · default: "false"

Enable speaker diarization (identify different speakers)

Response

text · string

Transcribed text

language · string

Detected or specified language code

confidence · number

Confidence score (0-1)

duration · number

Audio duration in seconds

words · array

Word-level details (if timestamps enabled)

words[].word · string

Individual word

words[].start · number

Start time in seconds

words[].end · number

End time in seconds

words[].confidence · number

Word confidence score

cURL

curl -X POST https://api.60db.ai/stt \
  -H "Authorization: Bearer your-api-key" \
  -F "audio=@recording.mp3" \
  -F "language=en" \
  -F "timestamps=true"

import { SixtyDBClient } from "60db";

const client = new SixtyDBClient("your-api-key");

const file = document.querySelector('input[type="file"]').files[0];

const result = await client.speechToText(file, {
  language: "en",
});

console.log("Transcription:", result.text);

from sixtydb import SixtyDBClient

client = SixtyDBClient('your-api-key')

with open('recording.mp3', 'rb') as audio_file:
    result = client.speech_to_text(audio_file, language='en')
    print(f"Transcription: {result['text']}")
    print(f"Confidence: {result['confidence']}")

Response

{
  "text": "Hello, this is a test of the speech to text API. It works great!",
  "language": "en",
  "confidence": 0.95,
  "duration": 5.2,
  "words": [
    {
      "word": "Hello",
      "start": 0.0,
      "end": 0.5,
      "confidence": 0.98
    },
    {
      "word": "this",
      "start": 0.6,
      "end": 0.8,
      "confidence": 0.97
    }
  ]
}