Documentation / Voice
Voice
Voice Agents use TTS (Text to Speech), which generates audio that LLMs generate during the course of a conversation. This is the audio that the end user having the conversation listens to.
Tigy AI provides managed text-to-speech for every voice agent. The platform exposes a curated set of Tigy AI voices; users cannot add external voice IDs or choose another TTS provider.
Warning
Voice providers receive the data needed to synthesize speech, such as generated text, selected voice, model settings, and request metadata. Review the provider's data processing, retention, model training, and regional hosting policies before using sensitive data.