Built with bolt.new

What if bolt.new could talk ?

TalkiTo adds voice and remote communication features to any app using any ASR or TTS provider. Perfect for AI agentic coders.

Self Hosting: Get Started

Quick Start Guide

Get TalkiTo running in minutes with your preferred setup

Chrome Extension Setup

Add voice control to any website including bolt.new, Claude, and more

1

Setup & Start Server

Clone the repository, install dependencies, and start the TalkiTo MCP SSE server

git clone https://github.com/robdmac/talkito.git cd talkito pip install -e ".[all]" talkito --mcp-sse-server
2

Install Chrome Extension

Load the extension into Chrome using developer mode

  1. Open Chrome and go to chrome://extensions/
  2. Enable "Developer mode" in the top right
  3. Click "Load unpacked"
  4. Select the extensions/chrome folder from your TalkiTo directory
3

Start Talking!

Right-click on any chat interface and select TalkiTo

  1. Navigate to bolt.new or any website with a chat
  2. Right-click on the chat input area
  3. Select "TalkiTo: Talk" from the menu and from then on all output will be spoken aloud
  4. Other options include "Talkito: WhatsApp" and "Talkito: Slack"

Application Setup

Add voice control directly to Claude Code and other desktop applications

1

Setup & Install

Clone the repository and install all required dependencies

git clone https://github.com/robdmac/talkito.git cd talkito pip install -e ".[all]"
2

Launch Claude Integration

Start TalkiTo with Claude desktop application support

talkito claude

See TalkiTo in Action

3

Configure TalkiTo

Speech input and output will now be live within the Claude application

  1. Claude will start and show the status of TalkiTo i.e.: 🟢 TTS (aws) | 🟢 ASR (assemblyai) | Comms: none
  2. Start speaking to interact with Claude using your voice!
  3. To turn TTS/ASR/Slack/Whatsapp on or off just type or say it i.e.: "turn off ASR"
4

Voice Commands

Use natural speech to control Claude and other applications

Speech-to-text input
Text-to-speech responses
Real-time conversation

Python Library

Integrate TalkiTo directly into your Python applications and scripts

1

Install TalkiTo

Install TalkiTo as a Python package with all dependencies

pip install talkito[all]
2

TTS Usage

Import and initialize TalkiTo in your Python script

from talkito import tts # Initialize TTS engine = tts.detect_tts_engine() tts.start_tts_worker(engine) # Speak text tts.queue_for_speech('Hello from the TTS module!')
3

ASR Usage

Import and initialize TalkiTo in your Python script

from talkito import asr # Define callback for recognized text def handle_text(text): print(f'You said: {text}') # Start dictation asr.start_dictation(handle_text)

Feature Comparison

See how TalkiTo compares to alternatives

Feature
TalkiTo Self-Hosted
TalkiTo Premium Coming Soon
WhisperFlow Competitor
Speech Recognition 8 Options Houndify, Whisper, Deepgram, AssemblyAI, AWS, Azure, Google, Whisper 8 Options Houndify, Whisper, Deepgram, AssemblyAI, AWS, Azure, Google, Whisper 1 Option Whisper
Text-to-Speech 6 Options OpenAI, ElevenLabs, AWS Polly, Azure, Google Cloud, Deepgram 6 Options OpenAI, ElevenLabs, AWS Polly, Azure, Google Cloud, Deepgram
WhatsApp Support
Slack Support
Any Application
Any Website
App coming soon
Hosted
Price Free TBD $12/month

Ready to Give Your Code a Voice?

View on GitHub