> ## Documentation Index
> Fetch the complete documentation index at: https://docs.destined.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Transcribe Audio

> Transcribe audio using multiple STT providers

## Request Body

<ParamField body="audio_url" type="string" required>
  URL to the audio file (WAV, MP3, or M4A)
</ParamField>

<ParamField body="providers" type="array" required>
  List of providers to use. Options: `deepgram-nova-3`, `deepgram-flux`, `assemblyai`, `openai`, `google`, `azure`, `amazon`, `soniox`, `playht`
</ParamField>

## Response

<ResponseField name="results" type="object" required>
  Object with provider names as keys and transcription results as values
</ResponseField>

<RequestExample>
  ```bash cURL theme={null}
  curl -X POST "https://api.destined.ai/v1/stt/transcribe" \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "audio_url": "https://example.com/audio.wav",
      "providers": ["deepgram-nova-3", "assemblyai", "openai"]
    }'
  ```

  ```typescript TypeScript theme={null}
  const results = await client.sttTesting.transcribeV1SttTranscribePost({
    audioUrl: "https://example.com/audio.wav",
    providers: ["deepgram-nova-3", "assemblyai", "openai"],
  });
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "results": {
      "deepgram-nova-3": {
        "transcript": "Hello, this is a test.",
        "latency_ms": 450,
        "confidence": 0.98
      },
      "assemblyai": {
        "transcript": "Hello, this is a test.",
        "latency_ms": 620,
        "confidence": 0.97
      },
      "openai": {
        "transcript": "Hello, this is a test.",
        "latency_ms": 850,
        "confidence": 0.95
      }
    }
  }
  ```
</ResponseExample>