voice-ai

voiceblender: Build Custom Voice Solutions

Name: voiceblender: Build Custom Voice Solutions
Author: VoiceBlender

Get programmable voice control with voiceblender, ideal for founders needing custom voice AI integrations.

116 stars20 forksGoGuide quality 8/10Updated 9/7/2026100% free · open source

What it does

Voiceblender provides a programmable voice platform for custom voice AI integrations, allowing founders to control SIP and WebRTC calls, mix multi-party audio, record conversations, and integrate with various AI agents through a REST API, webhooks, and WebSocket event stream.

When to use it

•When building a custom voice-controlled application that requires programmable call control and AI integration
•When needing to mix and record multi-party audio conversations in real-time
•When integrating with specific AI agents like ElevenLabs, VAPI, Pipecat, or Deepgram for advanced voice functionalities

Ready-to-paste prompt

curl -X POST -H 'Content-Type: application/json' -d '{"caller": "sip:user1@domain.com", "callee": "sip:user2@domain.com"}' http://localhost:8080/calls

Heads up: Make sure to obtain the necessary API keys for the AI agents you want to integrate with, such as ElevenLabs or Deepgram, as these are required for voiceblender to function correctly

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/voiceblender && curl -fsSL https://workflowstacks.com/api/skills/voiceblender/claude-skill -o ~/.claude/skills/voiceblender/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How voiceblender: Build Custom Voice Solutions works

Codeflow

Free to inspect

Voiceblender: Build Custom Voice Solutions is a very large Go project (~77k lines across 342 code files, plus 73 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size

Very large codebase

~77k lines · 342 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Go · Docker

No API keys detected

Go 100%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
CLAUDE.md
The instructions the AI actually follows
3
cmd/wavdump/main.go
Where the program starts running
4
go.mod
Dependencies and the commands it exposes
5
internal/agent/deepgram.go
Inside internal/ — the main logic begins here

What's in each folder

internal/Core code — the actual logic334 files

cmd/Command-line entry points5 files

examples/Examples you can copy13 files

certs/Folder1 files

docker/Deployment / infrastructure1 files

tests/Tests — proof it works75 files

.github/CI / automation (GitHub Actions)1 files

READMEHas testsDocumentedCI checksDocker readyExamples includedMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/voiceblender && curl -fsSL https://workflowstacks.com/api/skills/voiceblender/claude-skill -o ~/.claude/skills/voiceblender/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

VoiceBlender

Language