curl -X POST https://api.60db.ai/stt \
  -H "Authorization: Bearer your-api-key" \
  -F "[email protected]" \
  -F "language=auto" \
  -F "diarize=true" \
  -F "context=Cricket coaching session. Players: Arjun Mehta, Ishaan Verma. Discussing batting technique."

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, {
  // Omit language or pass "auto" for auto-detect
  language: "auto",
  diarize: true,
  // Optional: free-form context string enables LLM refinement on
  // proper nouns, filler removal, and punctuation.
  context:
    "Cricket coaching session. Players: Arjun Mehta, Ishaan Verma. Discussing batting technique.",
});

console.log("Transcription:", result.text);
console.log("Detected language:", result.language);
for (const seg of result.segments || []) {
  const speaker = seg.speakers?.[0]?.speaker ?? "unknown";
  console.log(`[${speaker}] ${seg.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='auto',   # omit or 'auto' for auto-detect
        diarize=True,
        # Optional: free-form context string enables LLM refinement on
        # proper nouns, filler removal, and punctuation.
        context='Cricket coaching session. Players: Arjun Mehta, Ishaan Verma. Discussing batting technique.',
    )
    print(f"Transcription: {result['text']}")
    print(f"Language: {result['language']} ({result['language_name']})")
    print(f"Duration: {result['duration_sec']}s")

{
  "request_id": "req_6822626d028743f5942526e0c08fa60c",
  "language": "en",
  "language_name": "English",
  "languages": null,
  "language_source": "fast_path",
  "duration_sec": 5.2,
  "processing_ms": 185,
  "rtf": 0.036,
  "text": "Hello, this is a test of the speech to text API. It works great!",
  "segments": [
    {
      "start": 0.0,
      "end": 3.1,
      "language": "en",
      "language_name": "English",
      "text": "Hello, this is a test of the speech to text API.",
      "confidence": 0.92,
      "words": [
        { "word": "Hello", "start": 0.0, "end": 0.32, "confidence": 0.94 },
        { "word": "this",  "start": 0.35, "end": 0.52, "confidence": 0.93 }
      ],
      "speakers": [
        { "speaker": "SPEAKER_00", "start": 0.0, "end": 3.1 }
      ]
    },
    {
      "start": 3.1,
      "end": 5.2,
      "language": "en",
      "language_name": "English",
      "text": "It works great!",
      "confidence": 0.89,
      "words": [],
      "speakers": [
        { "speaker": "SPEAKER_01", "start": 3.1, "end": 5.2 }
      ]
    }
  ],
  "words": [],
  "warnings": [],
  "warning_codes": [],
  "language_detection": {
    "mode": "fast_path",
    "candidates": ["en"],
    "segment_count": 2,
    "lid_calls": 0
  }
}

{
  "request_id": "req_...",
  "language": null,
  "language_name": null,
  "languages": null,
  "language_source": "fast_path",
  "duration_sec": 0.5,
  "processing_ms": 185,
  "rtf": 0.37,
  "text": "",
  "segments": [{ "start": 0.0, "end": 0.5, "text": "", "confidence": 0.85, "words": [] }],
  "words": [],
  "warnings": [
    {
      "code": "no_speech_detected",
      "message": "No speech detected in audio",
      "affected_segments": []
    }
  ],
  "warning_codes": ["no_speech_detected"],
  "language_detection": { "mode": "fast_path", "candidates": ["en"], "segment_count": 1, "lid_calls": 0 }
}