TalkiTo MCP server
Commit Aug 18, 2026Lets developers speak with Claude Code, Codex, and other AI agents, and receive spoken replies, Slack, WhatsApp, or SMS updates.
Also known as robdmac/talkito
- Stars
- 54
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Aug 18, 2026
- License
- AGPL-3.0
What is TalkiTo MCP?
TalkiTo lets developers speak with Claude Code, Codex, and other AI agents, and receive spoken replies, Slack, WhatsApp, or SMS updates.
Summary generated from the project's README
About TalkiTo MCP server
Interacting with AI agents through voice and messaging platforms is what TalkiTo enables for developers. This tool allows you to speak directly to Claude Code and OpenAI Codex, receiving spoken responses in return. It functions as a command-line tool, a Python library, or a web extension, and can be run as an MCP server using the mcp-sse-server command.
Users can customize their experience by selecting from various text-to-speech and speech-to-text providers. Options include cloud-based services like OpenAI, AWS Polly, Azure, Google Cloud, and ElevenLabs, or local, offline engines such as Kokoro, Piper, and local Whisper. For remote updates, the server can send notifications to Slack channels, WhatsApp recipients, or via Twilio SMS based on your environment configurations.
What you can do with it
- 1Web-based AI outputReceive spoken output from web agents like bolt.new or v0.dev via a browser extension.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
AZURE_SPEECH_KEYWHISPER_MODEL
| Name | Description | |
|---|---|---|
| AZURE_SPEECH_KEY | — | |
| WHISPER_MODEL | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablerobdmac/talkito is public and reachablegithub.com/robdmac/talkito ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-08-18github.com/robdmac/talkito ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubTalkiTo
TalkiTo lets developers talk, slack and whatsapp with Claude Code and OpenAI Codex. It can be used as a command-line tool, a web extension, and as a Python library.
🚀 Quick Install
Option 1: One-liner Install Script (Recommended)
curl -sSL https://raw.githubusercontent.com/robdmac/talkito/main/install.sh | bash
Option 2: PyPI
pip install talkito
Then just run:
talkito claude
Install for End Users
From Source (Stable)
# Clone the repository
git clone https://github.com/robdmac/talkito.git
cd talkito
# Create and activate virtual environment (recommended)
python3 -m venv venv
source venv/bin/activate
# Install system dependencies (macOS)
brew install portaudio
# Install package (normal install - gets updates via git pull)
pip install .
# Run this in a directory you want to use claude with
talkito claude
Install for Developers
Editable Install (Development)
# Clone the repository
git clone https://github.com/robdmac/talkito.git
cd talkito
# Create and activate virtual environment (recommended)
python3 -m venv venv
source venv/bin/activate
# Install system dependencies (macOS)
brew install portaudio
# Install in development mode (editable install)
pip install -e .
# Run this in a directory you want to use claude with
talkito claude
or for the web extension run as
talkito --mcp-sse-server
then go to chrome://extensions/ and load unpacked the extensions/chrome/ dir
Demo Video
AI Assistant Compatibility
| AI Assistant | Method | Status |
|---|---|---|
| Claude Code | Terminal | Fully Supported |
| Codex Cli | Terminal | Fully Supported |
| bolt.new | Web Extension | Output Only |
| v0.dev | Web Extension | Output Only |
| replit.com | Web Extension | Output Only |
| Other agents | Terminal | In Progress |
Run with Claude Code
run talkito claude
Run with Codex Cli
run talkito codex
Run as an MCP server
run talkito --mcp-server
Run the TalkiTo configuration menu
run talkito
Advanced Options
# Disable auto-skip to newer content (auto-skip is on by default)
talkito --dont-auto-skip-tts claude
# Use different TTS providers
talkito --tts-provider polly --tts-voice Matthew --tts-region us-west-2 echo "Hello with AWS"
talkito --tts-provider azure --tts-voice en-US-JennyNeural echo "Hello with Azure"
talkito --tts-provider gcloud --tts-voice en-US-Journey-F echo "Hello with Google"
talkito --tts-provider kittentts --tts-voice expr-voice-3-f echo "Hello with KittenTTS"
talkito --tts-provider kokoro --tts-voice af_heart echo "Hello with Kokoro (local)"
talkito --tts-provider piper --tts-voice en_US-lessac-medium echo "Hello with Piper (local)"
talkito --tts-provider neutts2e echo "Hello with NeuTTS (local)"
# Use different ASR providers
talkito --asr-provider gcloud --asr-language en-US claude
AZURE_SPEECH_KEY=... AZURE_SPEECH_REGION=eastus talkito --asr-provider azure claude
WHISPER_MODEL=small WHISPER_COMPUTE_TYPE=int8 talkito --asr-provider local_whisper claude
talkito --asr-language es-ES echo "Hola mundo" # Spanish recognition
# Enable remote communication (configure via environment variables)
talkito --slack-channel '#alerts' python manage.py runserver
talkito --whatsapp-recipients +1234567890 long-running-command
talkito --sms-recipients +1234567890,+0987654321 server-monitor.sh
Using tts.py (Standalone TTS)
The TTS module can be used independently for text-to-speech operations:
#!/usr/bin/env python3
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!")
# Wait and cleanup
import time
time.sleep(2)
tts.shutdown_tts()
Using asr.py (Standalone ASR)
The ASR module can be used independently for speech recognition:
#!/usr/bin/env python3
import asr
# Define callback for recognized text
def handle_text(text):
print(f"You said: {text}")
# Start dictation
asr.start_dictation(handle_text)
# Keep running (press Ctrl+C to stop)
try:
import time
while True:
time.sleep(1)
except KeyboardInterrupt:
asr.stop_dictation()
Provider Configuration
Text-to-Speech (TTS) Providers
System TTS (Default)
- macOS: Uses built-in
saycommand - Linux: Uses
espeak,festival, orflite(install via package manager) - Setup: No API key needed
OpenAI TTS
- Get API Key: https://platform.openai.com/api-keys
- Voices: alloy, echo, fable, onyx, nova, shimmer
- Usage:
--tts-provider openai --tts-voice nova
AWS Polly
- Get Credentials: https://aws.amazon.com/polly/getting-started/
- Setup: Set
AWS_ACCESS_KEY_IDandAWS_SECRET_ACCESS_KEY - Voices: Joanna, Matthew, Amy, Brian, and more
- Usage:
--tts-provider polly --tts-voice Matthew
Azure Speech Services
- Get API Key: https://azure.microsoft.com/en-us/services/cognitive-services/speech-services/
- Setup: Set
AZURE_SPEECH_KEYandAZURE_REGION - Voices: en-US-JennyNeural, en-US-AriaNeural, and many more
- Usage:
--tts-provider azure --tts-voice en-US-JennyNeural
Google Cloud Text-to-Speech
- Get Credentials: https://cloud.google.com/text-to-speech/docs/quickstart
- Setup: Set
GOOGLE_APPLICATION_CREDENTIALSto service account JSON path - Voices: en-US-Journey-F, en-US-News-N, and more
- Usage:
--tts-provider gcloud --tts-voice en-US-Journey-F
ElevenLabs
- Get API Key: https://elevenlabs.io/
- Setup: Set
ELEVENLABS_API_KEY - Voices: Various voice IDs available
- Usage: Configure in code or .env file
Deepgram
- Get API Key: https://deepgram.com/
- Setup: Set
DEEPGRAM_API_KEY - Voices: aura-asteria-en, aura-luna-en, aura-stella-en, and more
- Usage:
--tts-provider deepgram --tts-voice aura-asteria-en
KittenTTS (Local / Offline)
- Install:
pip install https://github.com/KittenML/KittenTTS/releases/download/0.1/kittentts-0.1.0-py3-none-any.whl soundfile phonemizer - Setup: No API key required. First run prompts to download the selected model (default
kitten-tts-nano-0.2) into the Hugging Face cache. ConfigureKITTENTTS_MODELandKITTENTTS_VOICEto pick different quality/voice options. - Best for: Ultra-lightweight CPU-only voices that stay on-device.
- Usage:
KITTENTTS_MODEL=kitten-tts-nano-0.2 talkito --tts-provider kittentts --tts-voice expr-voice-3-f
Kokoro (Local / Offline)
- Install:
pip install 'kokoro>=0.9.4' soundfile phonemizer - Setup: No API key required. TalkiTo will download Kokoro weights the first time you run it (set
KOKORO_LANGUAGE,KOKORO_VOICE,KOKORO_SPEEDto control defaults). - Best for: High-quality multilingual voices without sending audio to a cloud provider.
- Usage:
talkito --tts-provider kokoro --tts-voice af_heart --tts-language en-US
Piper (Local / Offline)
- Install:
pip install piper-tts - Setup: No API key required. A voice is a single ONNX file of a few tens of megabytes, downloaded on first use into
~/.cache/talkito/piper(setPIPER_VOICEandPIPER_VOICE_DIRto change the default voice or location). - Best for: The lightest offline option by a wide margin, and the fastest. It needs no torch at all, where the other local engines pull in hundreds of megabytes of runtime.
- Voices:
en_US-lessac-medium(default),en_GB-alan-medium,en_US-amy-mediumand many more — the menu lists a shortlist, but any name Piper publishes is accepted. Full list:python -m piper.download_voices --help - Usage:
talkito --tts-provider piper --tts-voice en_GB-alan-medium
NeuTTS 2E (Local / Offline)
- Install:
pip install neutts llama-cpp-python soundfile - Setup: No API key required. The first run downloads a quantized backbone and a decoder-only ONNX codec, around 600 MB together. Set
NEUTTS2E_VOICEandNEUTTS2E_EMOTIONto change the speaker and delivery. - Best for: Expressive, emotion-conditioned speech that stays on-device. It is a language model over a neural audio codec rather than a feed-forward synthesiser, so it sounds markedly less robotic than its size suggests.
- Speakers:
emily(default),paul,sophie,steven. Emotions:neutral,happy,sad,angry,surprised,fearful,disgusted. - Devices: On Apple Silicon the backbone runs on Metal automatically and falls back to CPU if unavailable.
NEUTTS_DEVICE=cpupins everything to CPU;NEUTTS_BACKBONE_DEVICEoverrides the backbone alone. - Usage:
NEUTTS2E_EMOTION=happy talkito --tts-provider neutts2e --tts-voice sophie
Automatic Speech Recognition (ASR) Providers
Google Speech Recognition (Default)
- Free: No API key required
- Limitations: Best for short utterances, requires internet
- Usage: Default when no provider specified
Google Cloud Speech-to-Text
- Get Credentials: https://cloud.google.com/speech-to-text/docs/quickstart
- Setup: Set
GOOGLE_APPLICATION_CREDENTIALS - Features: Better accuracy, streaming support
- Usage:
--asr-provider gcloud
AssemblyAI
- Get API Key: https://www.assemblyai.com/
- Setup: Set
ASSEMBLYAI_API_KEY - Features: Real-time transcription, speaker detection
- Usage: Configure in code or .env file
Deepgram
- Get API Key: https://deepgram.com/
- Setup: Set
DEEPGRAM_API_KEY - Features: Fast, accurate real-time transcription
- Usage: Configure in code or .env file
Houndify
- Get Credentials: https://www.houndify.com/
- Setup: Set
HOUNDIFY_CLIENT_IDandHOUNDIFY_CLIENT_KEY - Features: Natural language understanding
- Usage:
--asr-provider houndify
AWS Transcribe
- Get Credentials: https://aws.amazon.com/transcribe/
- Setup: Set AWS credentials
- Features: Streaming transcription
- Usage:
--asr-provider aws --aws-region us-west-2
Azure Speech Services
- Get API Key: https://azure.microsoft.com/en-us/services/cognitive-services/speech-services/
- Setup: Set
AZURE_SPEECH_KEYandAZURE_SPEECH_REGION, thenpip install azure-cognitiveservices-speech - Features: Low-latency streaming dictation with automatic punctuation
- Usage:
AZURE_SPEECH_KEY=... AZURE_SPEECH_REGION=eastus talkito --asr-provider azure
Local Whisper (On-Device)
- Install:
pip install faster-whisper(default) orWHISPER_COREML=1 pip install pywhispercppfor Apple Silicon/CoreML acceleration - Setup: No API key required. Configure
WHISPER_MODEL(e.g.,small,medium),WHISPER_DEVICE(cpu,cuda, ormps), andWHISPER_COMPUTE_TYPE(int8,int8_float16, etc.). Models are cached locally and TalkiTo will prompt before downloading unlessTALKITO_AUTO_APPROVE_DOWNLOADS=1. - Usage:
WHISPER_MODEL=small WHISPER_COMPUTE_TYPE=int8 talkito --asr-provider local_whisper
Communication Providers (Remote Interaction)
Twilio SMS
- Get Account: https://www.twilio.com/try-twilio
- Setup: Set
TWILIO_ACCOUNT_SID,TWILIO_AUTH_TOKEN,TWILIO_PHONE_NUMBERyou will need to a verified number to avoid being filtered. - Features: Send command output via SMS, receive input via SMS
- Usage:
--sms-recipients +1234567890
Twilio WhatsApp
- Get Started: https://www.twilio.com/whatsapp
- Setup Instructions: Run
talkito --setup-whatsappfor detailed setup guide - Required Environment Variables:
TWILIO_ACCOUNT_SID: Your Twilio account SIDTWILIO_AUTH_TOKEN: Your Twilio auth tokenTWILIO_WHATSAPP_NUMBER: Twilio's WhatsApp number (usually +14155238886)WHATSAPP_RECIPIENTS: Your WhatsApp numberZROK_RESERVED_TOKEN: Your zrok reserved share token
- Quick Setup:
- Join Twilio WhatsApp Sandbox at https://www.twilio.com/console/sms/whatsapp/sandbox
- Send the join code via WhatsApp to +1 415 523 8886
- Install zrok and create a reserved share:
zrok reserve public http://localhost:8080 - Set webhook URL in Twilio Console to:
https://YOUR-TOKEN.share.zrok.io/whatsapp
- Usage:
--whatsapp-recipients +1234567890
Slack
- Create App: https://api.slack.com/apps
- Setup: Set
SLACK_BOT_TOKENand optionallySLACK_APP_TOKEN - Features: Send output to channels, receive commands
- Usage:
--slack-channel '#channel-name'
Environment Configuration
Talkito supports two environment files:
.env- Primary configuration (takes precedence).talkito.env- Secondary configuration (won't override.env)
Copy .env.example to .env and add your API keys:
cp .env.example .env
# Edit .env with your API keys
For WhatsApp setup with zrok tunneling:
ZROK_RESERVED_TOKEN: Your zrok reserved share token for webhook tunneling
Requirements
- Python 3.10+
- macOS (with
saycommand) or Linux (withespeak,festival, orflite) - Optional:
SpeechRecognitionandpyaudiofor ASR support - Optional: Provider-specific Python packages (installed as needed)
Contributing
See CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.
License
This project is licensed under the GNU Affero General Public License v3.0 or later - see the LICENSE file for details.
Copyright (C) 2025 Robert Macrae
TalkiTo MCP questions
How do I run TalkiTo with Claude Code?
Install the package and run 'talkito claude' in the directory where you want to use Claude Code.
Can TalkiTo run as an MCP server?
Yes, running 'talkito --mcp-server' starts it as an MCP server; '--mcp-sse-server' serves the web extension.
Does TalkiTo work without an API key?
Yes, the default system TTS and default Google speech recognition need no API key, and local engines like Piper and Kokoro run offline.
Which text-to-speech providers does TalkiTo support?
It supports system TTS by default, plus OpenAI, AWS Polly, Azure, Google Cloud, ElevenLabs, Deepgram, and local engines KittenTTS, Kokoro, Piper, and NeuTTS.
Can TalkiTo send updates to Slack or WhatsApp?
Yes, enable remote communication with flags like --slack-channel or --whatsapp-recipients when running a command.
