Switchboard Editor
Turn voice & audio ideas into working prototypes in minutes
Build and test right in your browser.
The audio graphs are built on top of the Switchboard SDK (with a C/C++ core) so they can subsequently be deployed across many platforms. The audio engine runs on-device, though individual nodes in the graph can be run on-device or in the cloud, depending on the node.
See how the Editor works
Examples of what can be built.
See how to build a local LLM audio engine in the Switchboard Editor. This demo shows the precise connections for Whisper, Silero VAD, Llama, and TTS nodes in the Switchboard Editor.
This demo shows the AudioShake.Separator node's function in the Switchboard Editor. It then uses the separated audio streams to demonstrate gain staging—setting the correct volume levels via multiple Gain nodes to avoid distortion and noise when mixing the signal back together.
Your creative amplifier
Think of it as Unity or Unreal, but for voice & audio apps. Ideal for:
Innovation and R&D teams
Product managers
Engineers
Ideas-people
Rapid prototypers
Anyone eager to explore and compare the latest in voice and audio AI
Use the form below to join the waitlist and secure early access, request a demo, or if you’d like to meet to discuss consulting and co-development opportunities (see Switchboard Labs).
If you’re a developer, you can start on your own. The SDK includes a free tier you can use immediately.