Getting started

Quickstart

Generate your first audio and transcribe your first recording in five minutes.

Create an API key in the dashboard. It is shown only once.
Send Alania a sentence; the response is a streaming WAV file.
Upload the same file to Duyu and get the text back.

1 · Speak

POSThttps://voice.patientdesk.ai/v1/audio/speech

curl https://voice.patientdesk.ai/v1/audio/speech \
  -H "Authorization: Bearer pd_live_..." \
  -H "Content-Type: application/json" \
  -d '{ "model": "alania-v1",
        "input": "Randevunuz yarın saat 14:05 için oluşturuldu.",
        "voice": "alania", "response_format": "wav" }' \
  --output randevu.wav

The response is playable from the first chunk: the WAV header comes first, then PCM16 as it is generated. Don't wait for the whole file.

2 · Transcribe

POSThttps://voice.patientdesk.ai/v1/audio/transcriptions

Try it

curl https://voice.patientdesk.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer pd_live_..." \
  -F file=@kayit.m4a \
  -F response_format=json

Response

{ "text": "Randevunuz yarın saat 14:05 için oluşturuldu." }

Then

Live streaming

From a microphone over WebSocket: a final after 500 ms of silence, partial drafts before it.

Playback in the browser

Play the stream chunk by chunk with Web Audio.