Welcome to VALSEA

VALSEA is an AI-powered audio and text processing platform. Build real-time and batch speech workflows, translation, annotation, and text analysis through a consistent API.

Quickstart API Reference

What Can You Do?

Capability	Description
Real-time Transcription (Speech-to-Text)	Stream live audio with automatic language detection, including Arabic and regional variants
Real-time Voice (Text-to-Speech)	Stream generated audio over WebSocket for low-latency playback
Batch Transcription (Speech-to-Text)	Upload a complete audio file and receive its transcript in one response
Batch Text-to-Speech	Generate a complete audio file from text in one request
Live Translation	Stream source-language transcripts and translated final text
Live Transcription + Translation	Add always-on correction and optional speaker diarization for meeting and conversation workflows
Text Translation	Translate text between supported languages with automatic source detection
Annotation, Clarification, and Conversion	Enrich, normalize, and transform text
Formatting and Sentiment Analysis	Turn transcripts into structured outputs and analyze sentiment and emotions

Quick Example

Transcribe an audio file in one batch API call:

curl -X POST https://api.valsea.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@meeting.wav" \
  -F "model=valsea-transcribe" \
  -F "language=english"

Response:

{
  "text": "Good morning everyone, let's start the standup..."
}

Next Steps

Authentication — Get your API key and start making requests
Real-time Transcription — Start with automatic language detection
API Reference — Full reference for all endpoints with code examples