F
licenseA
qualityA
maintenanceA Windows-native MCP server that lets Claude Desktop transcribe audio files locally using whisper.cpp, with no internet connection required.
13
19 npm
1
-
claude-voice-input
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@claude-voice-inputlisten to me"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
claude-voice-input
Serveur MCP local pour parler a Claude au lieu de taper. Utilise faster-whisper pour la transcription entierement locale — rien n'est envoye dans le cloud.
Architecture
graph LR
A[Microphone] -->|Audio| B[recorder.py]
B -->|WAV bytes| C[faster-whisper]
C -->|Texte| D[Serveur MCP]
D -->|stdio| E[Claude Code]
style A fill:#f9f,stroke:#333
style E fill:#58f,stroke:#333Related MCP server: simple-asr-mcp
Flux de fonctionnement
sequenceDiagram
participant U as Utilisateur
participant CC as Claude Code
participant MCP as Serveur MCP Voice
participant R as Recorder
participant W as Whisper
U->>CC: "ecoute-moi"
CC->>MCP: voice_listen(language="fr")
MCP->>R: record_audio()
R->>R: Capture micro + detection silence
R-->>MCP: WAV bytes
MCP->>W: transcribe(audio)
W-->>MCP: Texte transcrit
MCP-->>CC: "Bonjour, je voudrais..."
CC->>CC: Utilise le texte comme contexte
CC-->>U: Repond a l'instruction vocaleComposants
graph TD
subgraph "claude-voice-input"
S[server.py<br/>Serveur MCP FastMCP] --> R[recorder.py<br/>Capture audio + silence]
S --> W[faster-whisper<br/>Transcription locale]
end
subgraph "Outils MCP exposes"
T1[voice_listen<br/>Micro → texte]
T2[voice_transcribe_file<br/>Fichier → texte]
end
S --> T1
S --> T2Installation rapide
curl -fsSL https://raw.githubusercontent.com/Baseline-quebec/claude-voice-input/main/install.sh | bashLe script fait tout automatiquement :
Verifie Python 3.10+
Installe PortAudio si manquant
Clone le repo dans
~/.claude-voice-inputCree un venv dedie et installe les dependances
Configure le serveur MCP dans
~/.claude/settings.json
Avec un modele specifique
curl -fsSL https://raw.githubusercontent.com/Baseline-quebec/claude-voice-input/main/install.sh | WHISPER_MODEL=medium bashInstallation manuelle
git clone https://github.com/Baseline-quebec/claude-voice-input.git
cd claude-voice-input
# Dependance systeme (PortAudio)
sudo apt install portaudio19-dev # Ubuntu/Debian
brew install portaudio # macOS
# Installer
pip install -e .Ajouter dans ~/.claude/settings.json :
{
"mcpServers": {
"voice": {
"command": "/chemin/vers/venv/bin/claude-voice-input",
"env": {
"WHISPER_MODEL": "base",
"WHISPER_DEVICE": "auto",
"WHISPER_COMPUTE_TYPE": "int8"
}
}
}
}Configuration
Variables d'environnement
Variable | Defaut | Description |
|
| Modele Whisper (voir tableau ci-dessous) |
|
|
|
|
|
|
|
| Repertoire d'installation |
Modeles Whisper
quadrantChart
title Compromis vitesse vs qualite
x-axis Lent --> Rapide
y-axis Basse qualite --> Haute qualite
tiny: [0.9, 0.25]
base: [0.75, 0.45]
small: [0.5, 0.65]
medium: [0.3, 0.8]
large-v3: [0.1, 0.95]Modele | RAM | Vitesse | Qualite | Cas d'usage |
| ~1 Go | Tres rapide | Correcte | Tests, instructions simples |
| ~1 Go | Rapide | Bonne | Usage quotidien (recommande) |
| ~2 Go | Moyen | Tres bonne | Contexte technique |
| ~5 Go | Lent | Excellente | Dictee longue, accents forts |
| ~10 Go | Tres lent | Maximale | Transcription de precision |
Outils MCP
voice_listen
Enregistre depuis le microphone et transcrit au silence.
Parametre | Type | Defaut | Description |
|
|
| Code langue ( |
|
|
| Secondes de silence avant arret |
|
|
| Duree maximale d'enregistrement |
voice_transcribe_file
Transcrit un fichier audio existant.
Parametre | Type | Defaut | Description |
|
| — | Chemin du fichier (wav, mp3, m4a, etc.) |
|
|
| Code langue |
Exemples d'utilisation dans Claude Code
> ecoute-moi
[Claude appelle voice_listen, vous parlez, il recoit le texte]
> transcris le fichier ~/meeting.wav
[Claude appelle voice_transcribe_file]
> ecoute mes instructions en anglais
[Claude appelle voice_listen avec language="en"]Mise a jour
Relancer le script d'installation — il fait un git pull automatiquement :
curl -fsSL https://raw.githubusercontent.com/Baseline-quebec/claude-voice-input/main/install.sh | bashLicence
MIT — Baseline
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
MCP server for Speech-to-Text
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
MCP server for RiverScript, an AI transcription platform - fetches transcripts shared via a link.
Transcribe audio and video with Speechmatics speech-to-text from Claude and any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMinimal MCP server for local speech recognition using faster-whisper. Runs on CPU, no cloud required.MIT
- AlicenseAqualityAmaintenanceMCP server for audio transcription using local faster-whisper or OpenAI Whisper API, enabling multilingual transcription with optional GPT post-processing.3MIT
- AlicenseNot gradedqualityCmaintenanceLocal speech-to-text MCP server for Linux that transcribes audio via push-to-talk (Right Ctrl) and injects the text into Claude's input stream in Tmux.23Apache 2.0