Hey everyone, today we're launching the closed beta of voice_dev, the only fully programmable platform for building voice agents that scale. We created voice_dev after struggling with other solutions that either lacked the flexibility we needed to build our agent or forced us to manage our own infrastructure.

We wanted a platform that provides all the infrastructure to run a voice agent while being fully programmable in Python. Every platform we tried either lacked some of the necessary infrastructure to run an agent (forcing us to host Docker containers and handle scaling ourselves) or provided all the infrastructure but had limited customization options. They might let you bring your own voice model or LLM, for example, but you can’t easily program the agent to fit your specific use case in a normal language like Python unless you also host some or all of it yourself.

voice_dev solves these problems by offering a complete platform for deploying and running AI voice agents. The platform includes all of the necessary infrastructure to run your agent while also being fully programmable in python, ensuring you’re always free to customize your agent any way you want.

Check it out and request access if you’re interested in being one of the first developers to build on the platform! We'd love to hear your feedback.