Quickstart
Get up and running with the VALSEA API in under 5 minutes.
Prerequisites
- A VALSEA account (sign up)
- An API key (see Authentication)
- Credits in your account
POST/v1/audio/transcriptions
Batch Transcription
Upload an audio file (WAV, MP3, M4A, FLAC, OGG, or WEBM). This endpoint is OpenAI SDK compatible -- you can use the official OpenAI client libraries by pointing them at the VALSEA API base URL.
curl -X POST https://api.valsea.ai/v1/audio/transcriptions \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "file=@recording.wav" \
-F "model=valsea-transcribe" \
-F "language=english" \
-F "response_format=verbose_json"
POST/v1/translations
Translate Text
Translate the transcription to another language:
curl -X POST https://api.valsea.ai/v1/translations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "valsea-translate",
"text": "Good morning everyone",
"target": "chinese",
"source": "auto"
}'
POST/v1/sentiment
Analyze Sentiment
Determine the sentiment of your transcript:
curl -X POST https://api.valsea.ai/v1/sentiment \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "valsea-sentiment",
"transcript": "The meeting went really well, everyone was very positive about the new direction."
}'
POST/v1/formatting
Format Output
Transform a transcript into structured meeting minutes:
curl -X POST https://api.valsea.ai/v1/formatting \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "valsea-format",
"transcript": "Your transcript text here...",
"output_type": "meeting_minutes"
}'
Response Formats
All endpoints support two response formats via the response_format field:
json(default) — Minimal response with only essential fieldsverbose_json— Extended response with additional metadata
Available Models
Next Steps
Head to the API Reference to explore all endpoints with full code examples.