ElevenLabs CLI

The community-built command line for ElevenLabs AI audio workflows.

Install · Quick Start · Workflows · MCP · Ecosystem · Support

[!WARNING] This is an independent, community-built CLI and is not an official ElevenLabs release. For official platform docs, visit elevenlabs.io/docs.

Why ElevenLabs CLI

• Unified interface for TTS, STT, voice cloning, dubbing, and audio tooling
• Script-friendly output (--json) for automation and CI pipelines
• MCP server mode for AI assistants with tool filtering and safety controls
• Multi-channel distribution (Homebrew, Scoop, Cargo, Docker, source)

Installation

Channel	Command
Homebrew (macOS/Linux)	brew tap hongkongkiwi/elevenlabs-cli && brew install elevenlabs-cli
Scoop (Windows)	scoop bucket add elevenlabs-cli https://github.com/hongkongkiwi/scoop-elevenlabs-cli && scoop install elevenlabs-cli
Cargo (all platforms)	cargo install elevenlabs-cli
Cargo with MCP feature	cargo install elevenlabs-cli --features mcp
Docker	docker run --rm -e ELEVENLABS_API_KEY=your-key ghcr.io/hongkongkiwi/elevenlabs-cli tts "Hello"
From source	git clone https://github.com/hongkongkiwi/elevenlabs-cli.git && cd elevenlabs-cli && cargo install --path .

Quick Start

# 1) Set API key (or use: elevenlabs-cli config set api_key "..." )
export ELEVENLABS_API_KEY="your-api-key"

# 2) Generate speech
elevenlabs-cli tts "Hello from ElevenLabs CLI" --output hello.mp3

# 3) List voices
elevenlabs-cli voice list

# 4) Transcribe audio
elevenlabs-cli stt audio.mp3

[!TIP] Examples use elevenlabs-cli (the default binary name). If you want a shorter command, add an alias such as alias elevenlabs='elevenlabs-cli'.

Feature Surface

Area	Commands
Speech	tts, tts-stream, tts-timestamps, realtime-tts, stt
Voice	voice, voice-changer, voice-design, library, samples, pronunciation
Content	sfx, dialogue, music, dub, isolate, audio-native
Agent Platform	agent, converse, tools, projects, knowledge, rag, workspace
Platform Ops	history, usage, models, user, config, webhook, update, interactive
Developer UX	completions, global --json, optional mcp mode

Common Workflows

Text to Speech

elevenlabs-cli tts "Ship high-quality audio from the terminal" --voice Brian --output narration.mp3

Speech to Text with Speaker Diarization

elevenlabs-cli stt meeting.mp3 --diarize --num-speakers 3

Voice Cloning

elevenlabs-cli voice clone --name "My Voice" --samples voice1.mp3,voice2.mp3

Sound Effects

elevenlabs-cli sfx "A soft UI notification" --duration 3 --output notification.mp3

JSON for Automation

elevenlabs-cli --json voice list | jq '.[0].voice_id'

MCP Server Mode

Start the server:

elevenlabs-cli mcp

[!NOTE] mcp is available in builds that include the mcp feature (for example, cargo install elevenlabs-cli --features mcp).

Minimal client config:

{
  "mcpServers": {
    "elevenlabs": {
      "command": "elevenlabs-cli",
      "args": ["mcp"],
      "env": {
        "ELEVENLABS_API_KEY": "your-api-key"
      }
    }
  }
}

Security options:

elevenlabs-cli mcp --enable-tools tts,stt,voice
elevenlabs-cli mcp --disable-admin
elevenlabs-cli mcp --disable-destructive
elevenlabs-cli mcp --read-only

Configuration

Default config path: ~/.config/elevenlabs-cli/config.toml

api_key = "your-api-key"
default_voice = "Brian"
default_model = "eleven_multilingual_v2"
default_output_format = "mp3_44100_128"

[mcp]
enable_tools = "tts,stt"
disable_tools = "agents"
disable_admin = false
read_only = false

Available Models

Model	Best For
eleven_multilingual_v2	High quality synthesis across many languages
eleven_flash_v2_5	Lowest latency
eleven_turbo_v2_5	Balanced speed and quality
eleven_v3	Expressive and emotional speech
scribe_v1	Higher-accuracy speech-to-text
scribe_v1_base	Faster, lower-cost speech-to-text

Output Formats

Format	Use Case
mp3_44100_128	Default, broadly compatible
mp3_44100_192	Higher quality MP3
wav_44100	Editing and mastering
pcm_16000	Telephony and real-time systems
opus_48000_128	Streaming and WebRTC
ulaw_8000	Legacy telephony

Command Reference

Use elevenlabs-cli --help and elevenlabs-cli <command> --help for details.

Command	Description
tts	Text-to-speech synthesis
stt	Speech-to-text transcription
voice	Voice management (list, clone, edit, delete)
library	Shared/community voice library
isolate	Background-noise removal
voice-changer	Speech-to-speech voice transformation
dub	Dubbing and translation workflows
dialogue	Multi-speaker dialogue generation
sfx	Sound effect generation
music	Music generation
agent, converse, tools, projects	Conversational/agent features
knowledge, rag, workspace	Knowledge and workspace management
history, usage, models, user	Account/model/runtime information
config, webhook, update, interactive, completions	Tooling and operations
mcp	Model Context Protocol server mode

Ecosystem

Companion repositories and their README files:

Repository	Purpose	README
hongkongkiwi/action-elevenlabs-cli	GitHub Action wrapper for CI workflows	Open
hongkongkiwi/homebrew-elevenlabs-cli	Homebrew tap for releases	Open
hongkongkiwi/scoop-elevenlabs-cli	Scoop bucket for Windows installs	Open
hongkongkiwi/elevenlabs-cli-skill	AI-agent skill integration	Open

Resources

• ElevenLabs API Reference
• ElevenLabs Documentation
• Voice Library
• API Keys
• Status Page

Support

• Report a bug
• Request a feature
• Releases

Contributing

Contributions are welcome.

1. Fork the repository.
2. Create a feature branch.
3. Run tests and checks.
4. Open a pull request with context and examples.

License

MIT License. See LICENSE.