外掛標籤
開發者團隊
② 後台搜尋「LS AI Provider for ElevenLabs」→ 直接安裝（推薦）
原文外掛簡介
This plugin provides a third-party ElevenLabs integration for the PHP AI Client SDK. It enables WordPress sites to use ElevenLabs models for text-to-speech conversion and sound effects generation.
It is not affiliated with, endorsed by, or sponsored by ElevenLabs.
“LS” is the author’s initials, Lauri Saarni, because the WordPress.org plugin directory requires a plugin name to begin with a distinctive identifier rather than a generic description.
The plugin has no admin screens of its own. It registers ElevenLabs with the AI Client so that WordPress core and any other plugin built on the AI Client can use it, and it never contacts ElevenLabs until such a request is actually made. See “External services” below.
Features:
Text-to-speech conversion with high-quality ElevenLabs voices
Automatic voice selection — a prompt works without configuring a voice ID first
Long-form narration — text beyond the model’s per-request limit is narrated across several requests and returned as one audio file
Sound effects generation from text descriptions
Voice directory for discovering available voices (including cloned voices), cached per API key
Dynamic model discovery from the ElevenLabs API
Automatic provider registration
Available Capabilities:
TEXT_TO_SPEECH_CONVERSION — convert text to speech using any ElevenLabs TTS model
SPEECH_GENERATION — generate sound effects from text prompts
Requirements:
PHP 7.4 or higher
The PHP AI Client SDK must be loadable. WordPress 7.0 and later bundle it in core; earlier WordPress needs it provided via Composer (it is an SDK, not a plugin)
An ElevenLabs account and API key
External services
This plugin relies on the ElevenLabs API (https://api.elevenlabs.io) to generate speech and sound. It is the service the plugin exists to integrate with, so the plugin cannot function without it. No request is ever made automatically: every one is the direct result of code on your site asking the AI Client for a generation or for provider metadata, and no request is made at all until an ElevenLabs API key is configured.
The following requests can be made, always over HTTPS and always with your ElevenLabs API key in the xi-api-key request header:
POST https://api.elevenlabs.io/v1/text-to-speech/{voice_id} — sent when text-to-speech conversion is requested. The text to be narrated, the selected voice ID and model ID, and any voice or output settings you configured are sent. Text longer than the model’s per-request character limit is sent as several requests, each also carrying the neighbouring text so the voice keeps its intonation across the split.
POST https://api.elevenlabs.io/v1/sound-generation — sent when sound effect generation is requested. The text prompt describing the sound and any generation settings you configured are sent.
GET https://api.elevenlabs.io/v1/models — sent when the list of available models is requested, to discover which models your account can use, and when your API key is verified so that the Connectors screen can report whether it works. Only your API key is sent. When the model listing fails, the plugin falls back to a built-in model list; the result of a key verification is cached for 15 minutes so the request is not repeated on every page load.
GET https://api.elevenlabs.io/v2/voices — sent when the list of available voices is requested, including when a default voice has to be resolved automatically. Only your API key and pagination parameters are sent. The response is cached in a transient for 15 minutes per API key.
The service is provided by ElevenLabs (https://elevenlabs.io/). Your use of it is governed by their terms and privacy policy:
Terms of Service: https://elevenlabs.io/terms-of-use
Privacy Policy: https://elevenlabs.io/privacy-policy
