Cartesia Narrator

Build a storytelling agent with expressive speech using Cartesia’s Sonic 3 TTS

View Cartesia Narrator Example on GitHub

Check out the complete Cartesia Narrator example in our GitHub repository

In this example, we will build a storytelling narrator agent using Cartesia’s Sonic 3 TTS with Vision Agents. The agent narrates stories with expressive speech, leveraging Cartesia’s audio markup tags to customize the speech output with emotions, pauses, and vocal effects. The full tutorial and example can be found on GitHub.

What we will build

Our AI narrator will:

• Listen to story topics via voice input using Deepgram
• Generate creative narratives using OpenAI’s GPT-4o-mini
• Speak with highly expressive and customizable voice using Cartesia’s Sonic 3 TTS
• Use audio markup tags for enhanced speech control (emotions, pauses, emphasis)
• Run on Stream’s low-latency edge network