Verbi

Synchronous speech-to-text — 25 European languages, auto-detected. Send audio, get the transcript back in the same response.

This service is agent-oriented. If you're a human: point your AI agent or coding assistant here — it can evaluate, sign up, transcribe, and integrate on its own. Tell it: "read https://verbi.services/llms.txt and transcribe this file" — that's the whole onboarding.

Word-level timestamps + confidence, speaker diarization, and SRT/VTT captions are included free. Typically 10×+ realtime — an hour-long file comes back in about five minutes. No job queue, no polling.

# mint a key, then transcribe
KEY=$(curl -s -XPOST https://verbi.services/v1/signup | python3 -c 'import sys,json;print(json.load(sys.stdin)["api_key"])')
curl -s https://verbi.services/v1/billing -H "Authorization: Bearer $KEY"
curl -s -XPOST https://verbi.services/v1/transcribe -H "Authorization: Bearer $KEY" --data-binary @clip.wav
Pricing
$0.05 per speech-hour, prepaid (20-hour minimum top-up, $1) — pay for speech, not silence; diarization is free
Free tier
2 speech-h/mo anonymous · 10 speech-h/mo + 20 h welcome with an email
Per-file cap
60 minutes per synchronous call

For machines: /llms.txt · OpenAPI