Open Source Voice Agent Framework
Vibecode abank agentinminutes
50 lines of code. Any OpenAI-compatible LLM. VAD, turn-taking, fillers, interruptions, and low latency handled for you.
Live Demos
Prototype
with Gradbot
Each demo runs a live voice AI agent built with Gradbot. Click to start, then speak naturally.
Click to launch demo
Developer Experience
50 lines to your first agent
Gradbot gives you the event loop for voice agents.
You write the logic, it handles the rest.
main.py
python
import gradbot
voice = gradbot.flagship_voice("Emma")
config = gradbot.SessionConfig(
voice_id=voice.voice_id,
instructions="You are a helpful assistant.",
language=voice.language,
)
input_handle, output_handle = await gradbot.run(
session_config=config,
input_format=gradbot.AudioFormat.OggOpus,
output_format=gradbot.AudioFormat.OggOpus,
)- 1Unified Intelligence: STT, LLM, and TTS coordinated into one seamless loop.
- 2Bi-directional audio streaming with precision VAD and silence detection.
- 3Live transcription, captions generation, and tool calls handled in the same cycle.
- 4Seamless turn-taking, natural fillers, and barge-in handled automatically.
- 5Unlimited voices via instant or pro cloning on any OpenAI-compatible model.