Generate governed audio with ak:elevenlabs

Use ak:elevenlabs for three direct audio actions: turn text into speech, create an authorized instant voice clone, or generate a sound effect. The Skill uses the ElevenLabs API and bundled Python helpers, so a run can create local audio, consume provider quota, and, for cloning, add a persistent voice to the connected ElevenLabs account.

Choose a bounded audio action

Use ak:elevenlabs when

• You need text-to-speech from supplied text or a local text file.
• You have explicit authority to create an instant voice clone from clean audio samples.
• You need a described sound effect of up to 30 seconds.
• You can review pronunciation, identity, audio quality, rights, provider cost, and the intended distribution before using the result.

Choose another workflow when

• You need a complete video production with scripts, storyboards, mixing, and exports. Use ak:video.
• You need audio editing, normalization, transcoding, or mixing without an ElevenLabs generation request. Use an approved media-processing workflow.
• You want to clone a person without their informed consent or authorization.
• You need a conversational agent or music-composition integration. Those topics exist in the packaged knowledge base, but the direct invocation hint exposes speak, clone, and sfx rather than a dedicated route for them.

Prepare the provider and source material

Before you start:

• Complete Onboarding, and confirm Marketing Kit is installed for the current runtime and scope.
• Install Python and the packaged requirement elevenlabs>=1.0.0 in the approved environment.
• Make ELEVENLABS_API_KEY available through the approved secret mechanism and allow outbound requests to ElevenLabs.
• Confirm the account has the required feature access, quota, billing, and licensing for the selected operation.
• For speech, supply approved text or a local text-file path and an output path.
• For cloning, supply a voice name and one or more authorized audio files. The helper accepts MP3, WAV, M4A, OGG, FLAC, and WebM paths and recommends one to two minutes of clear source audio.
• For sound effects, provide a descriptive prompt and an optional duration no greater than 30 seconds.

See Runtime adapters for broader delivery differences.

Run the Skill

Name one direct action and state the output boundary. This speech example asks for a local draft only.

/ak:elevenlabs speak "Your data stays under your control." Use the approved Rachel voice, model eleven_multilingual_v2, save to assets/audio/privacy-intro.mp3, review pronunciation, and do not publish

/ak:elevenlabs speak "Your data stays under your control." Use the approved Rachel voice, model eleven_multilingual_v2, save to assets/audio/privacy-intro.mp3, review pronunciation, and do not publish

$ak:elevenlabs speak "Your data stays under your control." Use the approved Rachel voice, model eleven_multilingual_v2, save to assets/audio/privacy-intro.mp3, review pronunciation, and do not publish

Understand the direct actions and helper controls

The text-to-speech helper defaults to voice Rachel, model eleven_multilingual_v2, stability 0.5, similarity 0.75, and speed 1.0. Treat these as bundled defaults, not a promise that the voice or model remains available on the connected account.

Follow the audio stages

1. Confirm the action. The Skill resolves speak, clone, or sfx, input paths, output path, provider authority, consent, and publication boundary.
2. Validate local input. It checks text or files before sending data. A missing or unsupported sample should stop cloning.
3. Confirm the account effect. Speech and sound effects generate audio; cloning additionally creates a reusable voice in the ElevenLabs account.
4. Call the provider. The helper authenticates with ELEVENLABS_API_KEY, sends the request, and reports provider errors rather than fabricating audio.
5. Write or report the result. Speech and sound-effect chunks are written to the chosen output. Cloning reports the created name and voice ID.
6. Review before use. Listen for pronunciation, artifacts, unintended identity cues, misleading tone, silence, clipping, and rights concerns.

Keep consent, account mutation, and spend explicit

Never expose the API key in a prompt, generated file, log excerpt, or commit. Do not use generated or cloned audio for impersonation, deception, unauthorized endorsement, evasion of disclosure rules, or misleading testimony.

Review outputs and evidence

A complete run should report:

• The action, source text or sample paths, provider settings, and exact output path or returned voice ID.
• The provider response or a clear failure without a fabricated artifact.
• A listening review covering pronunciation, pacing, identity, artifacts, duration, and suitability for the approved context.
• Consent and rights status for source voices, scripts, music, and sound design.
• Quota or charge-relevant requests and any account or publication step still pending.

For cloning, retain the consent record and voice ID separately from public content. For TTS, compare names, dates, prices, and legal or medical wording against the approved script after listening; correct text does not guarantee correct pronunciation.

Troubleshoot safely

Continue with the Marketing Kit overview or Projects, artifacts, and checkpoints.

Know the current limits

• The direct argument hint is [action: speak|clone|sfx] [text-or-file]. Broader ElevenLabs references do not create additional routed actions.
• The current sound-effect helper accepts --loop and --influence, but its SDK request forwards only the prompt and optional duration. Do not claim the saved file is seamless or that prompt influence was applied without separate evidence.
• The cloning helper implements instant voice creation through voices.add; it does not perform the documented professional-cloning training workflow.
• Provider models, voices, language coverage, quotas, latency, prices, plan requirements, output formats, and licensing can change independently of the packaged Skill.
• Audio generation does not guarantee naturalness, identity fidelity, intelligibility, conversion, platform acceptance, or legal permission.