How It Works
When the LLM generates a response, it is passed to the TTS engine which renders it as speech before being streamed back to the user through the avatar. The whole process happens in under a second. The voice your agent uses is set via thevoice_id field in your agent configuration. Every voice has a unique ID — copy it from the Voice Library and paste it directly into your agent.
Setting a Voice
Set thevoice_id when creating or updating an agent via API:
You can also set the voice directly from the Create New Agent form in the Developer Portal without writing any code.
Choosing the Right Voice
What’s Next?
Voice Library
Browse all available voices and copy their IDs.
Providers
See all STT, LLM, and TTS providers available on TruGen.