API Documentation
API Reference
Viseme Prediction API for facial animation and speech synthesis
Welcome to the Mascotbot Viseme Prediction API documentation. This API provides two main capabilities for creating synchronized facial animations:
Process existing audio files to generate viseme predictions for facial animation. Ideal when you already have audio and need synchronized mouth movements.
Convert text to speech while simultaneously generating viseme predictions. Supports multiple TTS engines including ElevenLabs and Cartesia for high-quality voice synthesis.
Get a temporary URL (expires in 10 minutes) that can be used to connect to a Websocket proxy handling connection to your ElevenLabs Conversational AI agent and enrhching the websocket flow with visemes.
Available Endpoints
/v1/visemes - Process Audio for Visemes
Process existing audio files to generate viseme predictions for facial animation. Ideal when you already have audio and need synchronized mouth movements.
/v1/visemes-audio - Generate Speech and Visemes
Convert text to speech while simultaneously generating viseme predictions. Supports multiple TTS engines including ElevenLabs and Cartesia for high-quality voice synthesis.
/v1/get-signed-url - Generate a URL for a conversation via ElevenLabs Conversational AI with visemes
Get a temporary URL (expires in 10 minutes) that can be used to connect to a Websocket proxy handling connection to your ElevenLabs Conversational AI agent and enrhching the websocket flow with visemes.
Real-time Streaming
Both endpoints use Server-Sent Events (SSE) to provide real-time streaming responses, enabling low-latency playback and immediate visual feedback.Process Audio for Visemes
Convert existing audio files to viseme predictions for facial animation
Generate Speech and Visemes
Convert text to speech with synchronized viseme generation using multiple TTS engines
Generate a URL for ElevenLabs Conversational AI
Use your existing ElevenLabs Conversational AI Agent with visemes stream added on top.