[Suggestion] Chainlit conversational voice agent with Deepgram Agent SDK (Python)

[deepgram-robot]

What to build

A working example of a Chainlit conversational voice agent powered by Deepgram's Agent SDK. Chainlit is a popular Python framework for building conversational AI apps (13K+ stars) used widely for prototyping and deploying AI assistants, but there is no published example showing how to add real-time voice interaction using Deepgram.

Why this matters

Python developers building conversational AI apps with Chainlit currently have no reference for adding voice capabilities. Chainlit's built-in audio handling combined with Deepgram's Voice Agent API would let developers ship voice-enabled chatbots in minutes rather than days. This integration would surface Deepgram in Chainlit's ecosystem — a high-traffic discovery channel for AI developers.

Suggested scope

• Language: Python
• Framework: Chainlit (latest)
• Deepgram APIs: Voice Agent API (STT + TTS), optionally Audio Intelligence for sentiment/topic display
• What it demonstrates: Real-time voice conversation in a Chainlit app, with both text and voice input/output, function calling for tool use, and conversation history display
• Complexity: Medium — backend only, Chainlit handles the UI

Acceptance criteria

• Runnable with minimal setup (clone, add API key, run)
• README explains the pattern clearly
• Uses current SDK version
• Supports both text and voice input modes in the Chainlit interface
• Includes at least one function calling / tool use example
• Audio streams bidirectionally without noticeable lag

---

Raised by the DX intelligence system.