Transcription

An audio recording → accurate text with speakers and paragraph timestamps. Meetings, calls, voice notes.

POST/v1/transcribepaused, 10 credits, charged only on success30 calls a minute per key

Paused since 2026-08-19

Calls return 503 inference_unavailable. You are not billed for them. The reason is on the rail below.

The example in the published schema

charged 0 credits

auth (bearer key)
per-key throttle
validate body
balance precheck
run the capability
charge credits ON SUCCESS ONLY
JSON

503 paused since 2026-08-19 Audio transcription needs a multimodal provider we can run under a no-training agreement. Every other endpoint already does; this one is paused rather than served on terms that would contradict our privacy commitment.

The request body/v1/transcribe

{
  "audioUrl": "https://…/standup.mp3",
  "diarize": true
}

The responsepublished example

"error": { "code": "inference_unavailable" }

curl https://api.thecompound.tech/v1/transcribe \
  -H "Authorization: Bearer $COMPOUND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audioUrl":"https://…/standup.mp3","diarize":true}'

Scored

This endpoint has no scored run in the latest eval suite. Every endpoint's score

The Media & agents guide has this endpoint with its example response. The reference has every parameter.

More from Media & agents

Agent memory $0.02/operationStore, search, and forget memories for your agents, semantic recall on your own namespace, no vector DB to run.Image generation $0.10/imageA prompt → a production-ready image. Marketing visuals, product scenes, and consistent brand imagery.Text to speech $0.05/clipText → natural speech audio, ready to embed. Voice notes, IVR lines, narration.

Get a key and buy credits