Skip to content

Alania · TTS

Voice designPreview

Describe a voice in words with voice_description, and Alania-2 creates a new voice for that request. No recording needed.

curl https://voice.patientdesk.ai/v1/audio/speech \
  -H "Authorization: Bearer pd_live_..." \
  -H "Content-Type: application/json" \
  -d '{ "model": "alania-v2",
        "input": "Merhaba, siparişiniz yarın öğleden önce teslim edilecek.",
        "voice_description": "A young man with a clear, energetic voice",
        "seed": 42 }' \
  --output tasarim.wav

Writing a description

  • Write it in English. Describe age, gender, timbre, pace and energy.
  • At most 200 characters. No parentheses.
  • Examples: A young man with a clear, energetic voice · A calm middle-aged woman with a warm, low voice.

Rules

  • When voice_description is present, voice is ignored. The OpenAI SDKs always send voice, so this is deliberate.
  • It cannot be combined with instructions or reference_audio (conflicting_fields).
  • A designed voice is not saved. Every part of a long text is read in the same voice.
  • To get the same result again, send a seed: the same seed, description and text give the same audio.
  • The default cfg is 3.0 for design (2.0 otherwise); a higher value holds the voice closer to the description.