vaaya / catalog / transcribe audio

Transcribe audio for AI agents

Audio or video in, accurate transcript out — with speaker labels and timestamps if you want them.

What it's for

Turn a call recording, podcast, voicemail, or interview into text.

Speaker labels (diarization) and timestamped segments on request.

Handles video files too — it transcribes the audio track.

Nova-3 accuracy, priced per audio minute.

Connect Vaaya, then just say it in plain language. For example:

❯Use Vaaya to transcribe this call recording with speaker labels.

❯Use Vaaya to transcribe this podcast episode and summarize it.

{
  "results": { "channels": [ { "alternatives": [ { "transcript": "Thanks for calling…" } ] } ] },
  "metadata": { "duration": 312.4 }
}

1¢ per audio minute. Billed per call in cents, capped by your max, every call on the ledger. Failed calls are not billed.

Connect Vaaya once, then describe the outcome. It picks the right tool, runs it, and pays per call.

npx @vaaya/mcp install