The Speech-to-Video API expects the agent’s spoken response audio (typically your TTS output) as input, not the user’s raw microphone audio. To create your own Conversational Video Agent, run the user audio through your own STT → LLM → TTS pipeline first, then forward the TTS output to the Speech-to-Video API.
When to Use This
Choose Speech-to-Video when you need:- Component-Level Control: Complete management of turn detection, STT, LLM, and TTS components
- Complex Tool Calling: Flexible LLM integrations with external APIs and databases
- Voice Infrastructure Migration: Seamless upgrade path for existing voice agent infrastructure
Pipeline Overview
1
Your Voice Agent Pipeline
You manage media transport, turn detection, STT, LLM, and TTS components
2
Beyond Presence Speech-to-Video API
Receives audio input from your pipeline
3
Avatar Video Output
Beyond Presence manages avatar generation and video streaming
Supported Frameworks
We support integration with popular voice agent frameworks including LiveKit, allowing you to add avatar video to your existing voice pipelines.LiveKit Plugin
Add avatars to your LiveKit agents with our plugin
Other Integration Options
Web & Mobile
Add Beyond Presence Managed Agents to your website or web app.
n8n Workflows
No-code workflow automation for managing conversations with Beyond Presence Managed Agents.