I’m using the updated latest Convai plugin with a MetaHuman in Unreal Engine 5.6. The chatbot responds correctly in text, but the character never plays voice, lip-sync, or talking animations. The output log repeatedly shows “TTS generation error: 400 — only Chirp 3: HD voices are supported for streaming synthesis.” When I select Google (GCP) voices, there is no audio at all; when I select Convai voices, audio plays but always sounds male even if a female voice is chosen. It seems the streaming TTS fails or falls back, so the MetaHuman never receives proper speech animation events.
Hello,
Welcome to the Convai Developer Forum!
The error only Chirp 3: HD voices are supported for streaming synthesis means you are not using a GCP Chirp voice.
Please switch your character’s voice to one of the GCP voices whose name/description clearly specifies style and language, for example:
Despina (Smooth, Gentle Japanese Female Voice)
These are the Chirp HD voices and are the only GCP voices that support streaming TTS in the latest plugin. The older GCP voices are being deprecated.
1 Like