Hi everyone 👋 I’m currently building an AI phone assistant for HR / candidate screening interviews and wanted to ask for your experience and recommendations. What do you think is the best voice model for a phone-based interview assistant in German? Key requirements for this use case are: • natural and professional tone • neutral but empathetic delivery • good German pronunciation • low latency for live conversations • stability over ~10–15 minute calls If you’ve tested different voice models (e.g. ElevenLabs, Cartesia, Azure, Rime, Vapi voices), I’d love to hear: • which model you chose • why you chose it • any trade-offs you noticed (latency vs. naturalness, etc.) Thanks a lot in advance! 🙏

For a professional, low-latency German voice assistant, Azure's "de-DE-KatjaNeural" is highly recommended for its natural tone and stability. You can configure it as follows:

json
{
  "voice": {
    "provider": "azure",
    "voiceId": "de-DE-KatjaNeural"
  }
}

This setup ensures high-quality German pronunciation and seamless performance for live HR interviews. For best results, test the voice in your workflow and adjust as needed for your use case. Source: See multilingual voice setup guidance in the documentation.

sounds waaayy to stiff

If you want the most natural voice possible, you should use GPT Realtime, be aware it will be costly.