File Import

Budget check → Upload audio → Track processing progress → Retrieve results

curl -X POST "https://vas-poc.vurbo.ai/api/v1/imports/check-quota" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"duration_ms": 3600000}'

{
  "data": {
    "allowed": true,
    "remaining_budget": 48.48,
    "is_unlimited": false,
    "duration_minutes": 25,
    "estimated_cost": 0.4236,
    "remaining_minutes": 2864
  }
}

curl -X POST "https://vas-poc.vurbo.ai/api/v1/imports" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "file=@meeting.mp3" \
  -F 'transcription_languages=["zh-TW"]' \
  -F 'translation_languages=["en-US"]' \
  -F "recognition_mode=multi_speaker"

curl -X POST "https://vas-poc.vurbo.ai/api/v1/imports" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "file=@meeting.mp3" \
  -F 'transcription_languages=["zh-TW"]' \
  -F 'translation_languages=["en-US"]' \
  -F "recognition_mode=multi_speaker" \
  -F "summary_template=meeting" \
  -F 'terminology={"zh-TW": [{"term": "語者分離", "boost": 1.5}]}' \
  -F 'translation_dict=[{"source": "語者分離", "translations": {"en-US": "Speaker Diarization"}}]'

{
  "data": {
    "import_id": "550e8400-e29b-41d4-a716-446655440000",
    "status": "pending",
    "stage": null,
    "progress": 0,
    "message": null,
    "original_filename": "meeting.mp3",
    "file_size": "15.2 MB",
    "task_id": null,
    "created_at": "2026-01-15T10:00:00.000Z"
  }
}

curl -X GET "https://vas-poc.vurbo.ai/api/v1/imports/{importId}" \
  -H "X-API-Key: YOUR_API_KEY"

{
  "data": {
    "import_id": "550e8400-e29b-41d4-a716-446655440000",
    "status": "processing",
    "stage": "transcribing",
    "progress": 45,
    "message": "Recognizing speech...",
    "task_id": null,
    "error_code": null,
    "error_message": null
  }
}

pending → processing → completed
                    └→ failed

async function pollImportStatus(importId, apiKey) {
  const interval = setInterval(async () => {
    const response = await fetch(
      `https://vas-poc.vurbo.ai/api/v1/imports/${importId}`,
      { headers: { 'X-API-Key': apiKey } }
    );
    const result = await response.json();
    const { status, stage, progress, task_id } = result.data;

    console.log(`Status: ${status}, Stage: ${stage}, Progress: ${progress}%`);

    if (status === 'completed') {
      clearInterval(interval);
      console.log(`Processing complete! Task ID: ${task_id}`);
      // Use task_id to load the results...
    } else if (status === 'failed') {
      clearInterval(interval);
      console.error(`Processing failed: ${result.data.error_message}`);
    }
  }, 5000); // Query every 5 seconds
}

const sentences = [];
// ... process SSE events and collect init_sentence

if (sentences.length === 0) {
  // Display empty state
  showEmptyState({
    title: 'No speech content was recognized in this audio file',
    hint: 'Possible reasons: volume too low, silence throughout, or a recognition language that does not match the audio. We recommend verifying the audio quality or adjusting the recognition language before uploading again.',
  });
} else {
  renderTranscript(sentences);
}

curl -X GET "https://vas-poc.vurbo.ai/api/v1/tasks" \
  -H "X-API-Key: YOUR_API_KEY"

const response = await fetch(
  `https://vas-poc.vurbo.ai/api/v1/sse/history/transcribe/${taskId}`,
  { headers: { 'X-API-Key': apiKey } }
);
// Process SSE events: init_metadata → init_sentence × N → init_summary → init_done

const response = await fetch(
  `https://vas-poc.vurbo.ai/api/v1/sse/audio/${taskId}`,
  { headers: { 'X-API-Key': apiKey } }
);
const blob = await response.blob();
const audio = new Audio(URL.createObjectURL(blob));
audio.play();

const response = await fetch(
  `https://vas-poc.vurbo.ai/api/v1/sse/retranslate/${taskId}?targetLang=ja-JP`,
  { headers: { 'X-API-Key': apiKey } }
);
// Process SSE events: translation × N → done

{
  "zh-TW": [
    { "term": "語者分離", "boost": 1.5 },
    { "term": "CVD製程", "boost": 2.0 }
  ]
}

{
  "zh-TW": [
    { "correct": "語者分離", "incorrect": ["語這分離", "語者分力"] }
  ]
}

[
  {
    "source": "語者分離",
    "translations": {
      "en-US": "Speaker Diarization",
      "ja-JP": "話者分離"
    }
  }
]

curl -X POST "https://vas-poc.vurbo.ai/api/v1/imports" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "file=@meeting.mp3" \
  -F 'transcription_languages=["zh-TW"]' \
  -F "recognition_mode=multi_speaker" \
  -F "callback_url=https://your-server.com/webhooks/vas"

           ┌────────────────────┐
           │   check-quota      │  Check whether the budget is sufficient
           │  POST /imports/    │
           │  check-quota       │
           └────────┬───────────┘
                    │
              allowed: true?
               ╱          ╲
            Yes            No → Prompt that the budget is insufficient
              │
    ┌─────────▼──────────┐
    │    POST /imports    │  Upload the audio
    │  multipart/form-data│  (transcription_languages,
    │                     │   translation_languages,
    │                     │   recognition_mode, ...)
    └─────────┬──────────┘
              │
         HTTP 202
         import_id
              │
    ┌─────────▼──────────┐
    │  GET /imports/{id}  │  Poll the processing status
    │   every 3 to 5 s    │  (query every 3 to 5 seconds)
    └─────────┬──────────┘
              │
        status check
       ╱      │      ╲
   pending  processing  completed / failed
              │              │
         stage:          task_id ←── Processing complete
         converting          │
         transcribing   ┌────▼─────────────┐
         translating    │  Tasks API        │  View the task list
         summarizing    │  SSE History API  │  Load the transcript
                        │  SSE Audio API    │  Play the audio
                        │  SSE Retranslate  │  Retranslate
                        └──────────────────┘