Audio API

Provides speech-to-text (STT) and text-to-speech (TTS) capabilities.

Speech to Text (STT)

Convert audio files to text with multi-language support:

bash

curl -X POST "https://api.tk-novalink.com/v1/audio/transcriptions" \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -F model="whisper-1" \
  -F file="@audio.mp3"

Text to Speech (TTS)

Convert text to speech with multiple voices:

bash

curl -X POST "https://api.tk-novalink.com/v1/audio/speech" \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello world!",
    "voice": "alloy"
  }' --output speech.mp3

Supported Models

Model	Type	Description
whisper-1	Speech recognition	Multilingual STT
tts-1	Speech synthesis	Standard TTS
tts-1-hd	Speech synthesis	HD TTS

Balance API