Elevenlabs

Elevenlabs

Tools for the ElevenLabs AI-audio API: convert text to spoken audio in any of the account's voices, generate sound effects and multi-speaker dialogue, re-voice or denoise existing audio, transcribe audio and video by URL, design brand-new synthetic voices from a text description, and manage the account's voices, generation history, and credit quota. Audio-producing tools write the audio to a local file and return its path by default; pass return_base64: true to get the bytes inline instead (for consumers without filesystem access).

Independent, unofficial connector for Elevenlabs. Not affiliated with, endorsed by, or sponsored by Elevenlabs. "Elevenlabs" is a trademark of its owner, used only to identify the service this connector works with.

When to use this

• Turn text into audio: narration, a spoken reply, a podcast-style dialogue, or a sound effect described in words.
• Transform existing audio: transcribe it, isolate the speech from background noise, or re-voice it in a different voice.
• Manage voices: find one in the account or the community library, add it, design a new one from a description, or free up voice slots.
• Check the account before big generations: remaining character credits, tier gates, and voice-slot usage via getUserSubscription.

Setup

This is an agentskills.io skill.

If the connector has not been installed as a skill yet, install it first with npx skills add zapier/connectors --skill elevenlabs (or your harness's own skill-install mechanism), then continue here. Installing the skill copies these files, not dependencies. Before running the CLI, a local MCP server, or zapier-sdk auth commands, run npm install --omit=dev here once. Importing the published package as a dependency in your own project instead? That npm install already resolves everything — see references/use-as-sdk.md.

Want the actual repo source instead — to browse references/, run this connector's tests, or hack on it? See README.md for a scoped git clone.

The connector runs on Node.js 22.18+. Pick the reference that matches how you're running it, and load it before doing anything else:

Scripts

All scripts share the single elevenlabs connection. Audio-producing scripts accept return_base64 (default false: audio is written to a temp file and returned as audio_path).

Disambiguation & refusals

Name-matched voices. Voices are looked up by human-friendly names (listVoices search, searchVoiceLibrary), and names collide — several account or library voices can share "George" or "Rachel". Before generating with, deleting, or adding a voice matched by name: count exact (case-insensitive) name matches. Exactly one → act on it without asking. Two or more → stop, list the candidates with a distinguishing field (category, description, or accent), and ask which one. Never silently pick. The same rule applies to history items matched by their source text via listHistory search before deleteHistoryItem.

Unsupported operations. This connector does not clone voices from sample recordings (instant or professional voice cloning) and does not generate music. If asked, say the operation isn't supported here and stop — don't substitute designVoice (which invents a voice from a description, not from someone's recording) or createSoundEffect (which makes sound effects, not music) and report success for an action you didn't perform.

Auth

Every shape passes auth as one connection selector, not the secret — a [<resolver>:]<value> string. Every connector accepts zapier:<connection-id> (Zapier-managed auth — routes through Zapier's auth, retries, and governance layer); some also accept one or more direct-token resolvers (naming and count vary per connector) — check this connector's own resolvers rather than assuming. The <resolver>: prefix is optional; a bare value goes to the first resolver that claims it — a UUID-shaped bare value always claims zapier:. Each script declares the connections it needs and the resolvers each accepts. The exact syntax for passing a connection (and how to see this connector's resolver list) differs by shape — see the reference you loaded above.

Checking what's already configured first? Don't dump environment values to do it — env or env | grep <name> prints the value along with the name, leaking a live credential into the transcript if one is set. Check names only (env | cut -d= -f1 | grep -i <name>) or test a known name directly ([ -n "$VAR_NAME" ]).

No connection yet? Pick one — and follow the reference's own flow to obtain it; never just ask the user for a connection id or token as if they already have one memorized:

Output format

Every script returns a { data, meta } envelope:

• data — the script's result (the shape its outputSchema declares; see the reference you loaded above for how to inspect a script's exact schema in your shape).
• meta.outputDataValidation — what validating data did:
  • { skipped: false, droppedPaths: null } — validated, nothing removed.
  • { skipped: false, droppedPaths: [...], instruction } — validated, but those paths were stripped from data: fields the script returned from the API that the outputSchema doesn't declare. If you need them, re-run with output validation skipped.
  • { skipped: true } — validation was bypassed; data is the raw, unchecked script output.

Reading dropped fields / skipOutputDataValidation. To receive the raw, unvalidated result, opt out of output validation (the exact syntax differs by shape — see the reference you loaded above). Input validation is never skipped.

Trimming the result / filterOutputData. To shrink a large result down to the fields you need, pass a jq expression that post-processes data (again, exact syntax per shape). The jq runs against data only, NOT the { data, meta } envelope, so write it rooted at data (run the script's --help — or your shape's equivalent — to see its output schema). The transformed value replaces data, meta is preserved, and the result is NOT re-validated against the output schema.

References

Load the matching reference file before working in that area: