AI Characters with SillyTavern

What it is:

A technology demonstration of a persona and voice clone system.

What I did:

Integrate multiple AI and voice synthesis tools.
Set up multiple local servers and connect external APIs to create a functional voice clone.
Technologies: SillyTavern, XTTS API server, SillyTavern-Extras server, OpenAI Whisper, Claude 3 Haiku, OpenRouter.ai, and SerpAPI.

Silly Tavern Demonstration Video

chatting with one's own voice

Read Full Post Details...

Silly Tavern demonstration – Persona/Voice clone

Posted on March 19, 2024

This is a technology demonstration (many local servers + external APIs). Talking to a self-clone.

Exploring possibilities for using one’s own voiice in cognitive science and psychology research. Does hearing one’s own voice change perception of received message?

Potential areas to explore include the impact on self-perception, learning and retention, confidence and self-efficacy, therapy and mental health applications, and advancements in human-computer interaction.

This demo brings together many technologies: SillyTavern, XTTS API server, SillyTavern-Extras server, OpenAI Whisper, and Claude 3 Haiku, connected through multiple servers and environments

SillyTavern: https://github.com/SillyTavern
XTTS API server: https://github.com/daswer123/xtts-api-server
SillyTavern-Extras server: https://github.com/SillyTavern/SillyTavern-Extras
OpenAI Whisper: https://openai.com/research/whisper
Claude 3 Haiku: https://docs.anthropic.com/claude/docs/models-overview
OpenRouter.ai: https://openrouter.ai/
SerpaAPI: https://serpapi.com/

Please see and hear my demonstration video at the top