Endpoints
Media & agents
Voice, images, transcripts — and memory that persists.
Transcription
POST /v1/transcribe$0.10/recording
An audio recording → accurate text with speakers and paragraph timestamps. Meetings, calls, voice notes.
curl https://api.kynth.studio/v1/transcribe \
-H "Authorization: Bearer $KYNTH_API_KEY" \
-H "Content-Type: application/json" \
-d '{"audioUrl":"https://…/standup.mp3","diarize":true}'Example response
200 OK
{
"text": "Alright, quick standup. Priya, want to start? …",
"segments": [
{
"speaker": "Speaker 1",
"start": "00:00",
"text": "Alright, quick standup. Priya, want to start?"
},
{
"speaker": "Speaker 2",
"start": "00:04",
"text": "Sure — the duplicate-charge fix is reviewed…"
}
],
"language": "en",
"usage": {
"credits": 10,
"balanceRemaining": 217
}
}Agent memory
POST /v1/memory$0.02/operation
Store, search, and forget memories for your agents — semantic recall on your own namespace, no vector DB to run.
curl https://api.kynth.studio/v1/memory \
-H "Authorization: Bearer $KYNTH_API_KEY" \
-H "Content-Type: application/json" \
-d '{"op":"search","namespace":"agent-42","query":"what does the customer prefer for delivery?","limit":3}'Example response
200 OK
{
"op": "search",
"results": [
{
"id": "mem_8f3a…",
"content": "Customer prefers evening deliveries after 6pm, no signature.",
"score": 0.91,
"metadata": {
"source": "ticket-5561"
},
"createdAt": "2026-07-01T18:22:00Z"
}
],
"usage": {
"credits": 2,
"balanceRemaining": 215
}
}Image generation
POST /v1/image$0.10/image
A prompt → a production-ready image. Marketing visuals, product scenes, and consistent brand imagery.
curl https://api.kynth.studio/v1/image \
-H "Authorization: Bearer $KYNTH_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"A minimal hero image of a bamboo standing desk in warm morning light","style":"editorial photography","aspectRatio":"16:9"}'Example response
200 OK
{
"image": "<base64…>",
"mimeType": "image/png",
"revisedPrompt": null,
"usage": {
"credits": 10,
"balanceRemaining": 205
}
}Text to speech
POST /v1/speak$0.05/clip
Text → natural speech audio, ready to embed. Voice notes, IVR lines, narration.
curl https://api.kynth.studio/v1/speak \
-H "Authorization: Bearer $KYNTH_API_KEY" \
-H "Content-Type: application/json" \
-d '{"text":"Your order has shipped and will arrive Thursday.","pace":"normal"}'Example response
200 OK
{
"audio": "<base64…>",
"mimeType": "audio/wav",
"durationSec": 3.4,
"usage": {
"credits": 5,
"balanceRemaining": 200
}
}