elevenlabs-tts

ElevenLabs eleven_v3 text-to-speech with 12 curated multilingual voices and stability/similarity/style controls. Great for dubbing, audiobooks, and character dialog. Before picking a voice, you can search for the right one via elevenlabs-search.

Overview

Field	Value
Model ID	`elevenlabs-tts`
CLI	`dlazy elevenlabs-tts`
MCP	`elevenlabs-tts` (Claude Code surfaces this as `mcp__dlazy__elevenlabs-tts`)
Type	`audio`
Execution	Async task; the CLI polls until completion (`--no-wait` returns `generateId` immediately)
Batch	Supports `--batch <n>` parallel fan-out

Parameters

Arg	Type	Required	Notes
`prompt`	string	Yes	Prompt
`use_custom_voice`	string	No	Use Custom Voice; default `false`
`custom_voice_id`	string	No	Custom Voice ID (click search to browse the library or paste a voice_id); only when use_custom_voice=true
`voice_language`	"multilingual"	No	Voice Language; default `"multilingual"`
`voiceId`	string	No	Voice ID Options depend on "voice_language"; default `"21m00Tcm4TlvDq8ikWAM"`; only when use_custom_voice=false; options depend on `--voice_language` (see "Dynamic Options")
`stability`	string	No	Stability; default `0.5`
`similarity_boost`	string	No	Similarity Boost; default `0.75`
`style`	string	No	Style; default `0`

--input @file.json or --input '{...}' can supply all args at once; flags take precedence over --input keys.

CLI Examples

dlazy elevenlabs-tts --help
dlazy elevenlabs-tts --prompt "Write your prompt here"
dlazy elevenlabs-tts --prompt "Write your prompt here" --dry-run
dlazy elevenlabs-tts --prompt "Write your prompt here" --no-wait
dlazy elevenlabs-tts --prompt "Write your prompt here" --batch 4

MCP

MCP is consumed by AI clients, not handwritten. Once dLazy is registered as an MCP server the tool appears in the client's tool list — Claude Code surfaces it as mcp__dlazy__elevenlabs-tts; generic clients (e.g. OpenClaw) call it as elevenlabs-tts.

See MCP setup for how to add the server.

Output

{
  "outputs": [
    { "type": "audio", "id": "o_...", "url": "https://files.dlazy.com/result.mp3", "mimeType": "audio/mpeg" }
  ]
}

Media tools emit image / video / audio / file outputs. Use --output url to print only the URLs on stdout.

Dynamic Options

`--voiceId` (depends on `--voice_language`)

when --voice_language multilingual:

ID	Name
`21m00Tcm4TlvDq8ikWAM`	Rachel · 知性女声
`EXAVITQu4vr4xnSDxMaL`	Sarah · 年轻女声
`AZnzlk1XvdvUeBnXmlld`	Domi · 自信女声
`MF3mGyEYCl7XYWbV9V6O`	Elli · 甜美女声
`ThT5KcBeYPX3keUQqHPh`	Dorothy · 温柔女声
`ErXwobaYiN019PkySvjV`	Antoni · 沉稳男声
`TxGEqnHWrfWFTfGW9XjX`	Josh · 年轻男声
`VR6AewLTigWG4xSOukaG`	Arnold · 清晰男声
`pNInz6obpgDQGcFmaJgB`	Adam · 深沉男声
`yoZ06aMxZJJ28mfd3POQ`	Sam · 沙哑男声
`onwK4e9ZLuTAKqWW03F9`	Daniel · 英伦男声
`pqHfZKP75CvOlQylNhV4`	Bill · 中年男声