← All templatestemplates / general-purpose-voice-agent-with-low-latency-streaming

Customupdated Jun 16, 2025 · other · other

General Purpose Voice Agent with Low Latency Streaming

A low-latency voice agent template demonstrating integration between AssemblyAI's Universal-Streaming API for speech recognition, OpenAI GPT-4 for conversational intelligence, and ElevenLabs for natural voice synthesis. Suitable for building custom voice assistants across various use cases.

No demo yetView source Fork template

The numbers

latency—

cost / min—

frameworkCustom

The stack

telephonyWeb Only

speech-to-textAssemblyAI Streaming

llmGPT-4o

text-to-speechElevenLabs Turbo v2.5

System prompt

No prompt published.

Config

config.json

{
  "debug_mode": false,
  "llm_provider": "OpenAI",
  "stt_provider": "AssemblyAI Universal-Streaming",
  "tts_provider": "ElevenLabs"
}

Voice AI recipes, picks, and analysis.

Get the useful new templates plus the occasional teardown of what’s working in production voice AI.