elevenlabs-search
Search the ElevenLabs voice library by keyword, source, and category. Returns a playable preview for each matched voice so you can pick the right one before running TTS. Search with ONE short English descriptor (deep / young / narrative); extra words narrow the match and full sentences usually return nothing.
Search the ElevenLabs voice library by keyword, source, and category. Returns a playable preview for each matched voice so you can pick the right one before running TTS. Search with ONE short English descriptor (deep / young / narrative); extra words narrow the match and full sentences usually return nothing.
Overview
| Field | Value |
|---|---|
| Model ID | elevenlabs-search |
| CLI | dlazy elevenlabs-search |
| MCP | elevenlabs-search (Claude Code surfaces this as mcp__dlazy__elevenlabs-search) |
| 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 | No | Sent verbatim to ElevenLabs as a substring search over each voice's name/labels — it is NOT split into OR'd keywords, so every extra word NARROWS the result and a full sentence usually matches nothing. Give ONE English descriptor (two at most). Good: deep, young, old, raspy, narrative, male, child. Bad: 'stern angry mature male boss scolding in mandarin'. Pick source/style with voice_type / category, not with more words here.; default "" |
voice_type | "any" | "personal" | "community" | "default" | "workspace" | "non-default" | "non-community" | "saved" | No | Voice source（any=Any; personal=My Voices; community=Community Library; default=Default; workspace=Workspace; non-default=Non-default; non-community=Personal + Workspace; saved=Saved）; default "any" |
category | "any" | "premade" | "cloned" | "generated" | "professional" | No | Category（any=Any; premade=Premade; cloned=Cloned (IVC); generated=AI Generated; professional=Professional (PVC)）; default "any" |
page_size | string | No | Result count; default 10 |
--input @file.jsonor--input '{...}'can supply all args at once; flags take precedence over--inputkeys.
CLI Examples
dlazy elevenlabs-search --help
dlazy elevenlabs-search --prompt "" --voice_type "any" --category "any"
dlazy elevenlabs-search --prompt "" --voice_type "any" --category "any" --dry-run
dlazy elevenlabs-search --prompt "" --voice_type "any" --category "any" --no-wait
dlazy elevenlabs-search --prompt "" --voice_type "any" --category "any" --batch 4MCP
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-search; generic clients (e.g. OpenClaw) call it as elevenlabs-search.
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.
elevenlabs-music
ElevenLabs music_v1 model — generates 10–300s original music from a natural-language prompt. Good for BGM, ads, and short-video soundtracks.
elevenlabs-sfx
ElevenLabs text-to-sound model — generates 1–22s short sound effects from a description. Suitable for foley, ambience, alerts, and game SFX.