LiveREST

Hear

Speech-to-text, telephony-native.

Whisper-compatible transcription tuned for 8 kHz call audio, with eager streaming partials and a half-price async batch tier. Drop it in by changing two lines of your OpenAI client.

Get a free key Read the docs

Price: $0.003/min
Endpoint: POST /v1/audio/transcriptions
Scope: hear:transcribe
Model id: pyai-hear-telephony

Batch (async, -50%)$0.0015/min

What you get

Built for the phone

Tuned on narrowband call audio, not podcast studio takes - so accuracy holds up on real lines.

Stream the words as they happen

Eager partials let you barge-in, endpoint, and react mid-utterance instead of waiting for the final.

Batch at half price

Queue long recordings to the async jobs API at $0.0015/min with webhooks on completion.

Telephony 8 kHz Streaming partials Whisper-compatible Async batch (-50%) Idempotent jobs

First partials in a few hundred milliseconds; sync files return in well under real-time.

Start in minutes

cURL

curl https://api.pyai.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $PYAI_KEY" \
  -F model=pyai-hear-telephony \
  -F file=@call.wav

FAQ

Is it OpenAI-compatible?

Yes. Point your existing OpenAI SDK at https://api.pyai.com/v1 and pass your PyAI key - the request/response shapes match.

Does it stream?

Yes, over the streaming transcription surface; you receive partial and final results per utterance.

Build with Hear today.

Start free with $50.00 in credit - no card. Your test key works instantly.

Get a free key Model your spend

No credit card - OpenAI-compatible - cancel anytime