Access Gemini fine-tuned, Whisper, and YiddishLabs through one endpoint. Credit-based. No monthly fees.
curl -X POST https://asr-api.kohnai.ai/v1/transcribe \ -H "Authorization: Bearer ak_live_7f3a9b2e..." \ -H "Content-Type: application/json" \ -d '{ "model": "whisper", "audio_url": "https://storage.example.com/shiur-42.mp3", "audio_duration_seconds": 120 }' # Response (200 OK) { "text": "אין יענעם יאר האבן מיר זיך אלע צוזאמענגעקליבן...", "model": "whisper", "duration_minutes": 2.0, "credits_used": 6, "remaining_credits": 994 }
Each model is optimized for different use cases and recording types.
Highest accuracy. Google Gemini fine-tuned on Yiddish speech via Vertex AI. Ideal for archival Rebbe recordings and lectures.
Fast and affordable. GPU-accelerated Whisper fine-tuned on Yiddish. Excellent cost-to-accuracy ratio for bulk processing.
Broadcast and modern Yiddish specialist. Commercial-grade ASR from YiddishLabs for conversational and media content.
A single REST endpoint. No SDKs required.
Sign up with your email, confirm, and generate an API key from the dashboard. Keys start with ak_live_.
Purchase a credit pack. Credits never expire. Start with 1,000 for $10 or pick a larger pack.
Send your audio URL to /v1/transcribe with your chosen model. Receive Yiddish text in seconds.
1 credit = $0.01. Credits never expire. Buy once, use any model.