Skip to content
PEKPIK LLM PEKPIK LLM Docs

Audio

Transcription

Section titled “Transcription”

POST https://aiapiv2.pekpik.com/v1/audio/transcriptions

Terminal window
curl https://aiapiv2.pekpik.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $PEKPIK_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1"
  • 99-language speech recognition.
  • Output formats: json, text, srt, vtt.
  • Typical max file size 25 MB.

Text-to-speech

Section titled “Text-to-speech”

POST https://aiapiv2.pekpik.com/v1/audio/speech

Terminal window
curl https://aiapiv2.pekpik.com/v1/audio/speech \
  -H "Authorization: Bearer $PEKPIK_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","voice":"alloy","input":"Hello from PEKPIK LLM"}' \
  --output speech.mp3
  • Multiple voices and output formats (mp3, wav, opus, aac, flac, pcm).
  • Maximum input around 4096 characters per request.