[WordPress] 外掛分享: Speak Input – Voice Dictation for ACF

首頁外掛目錄 › Speak Input – Voice Dictation for ACF
WordPress 外掛 Speak Input – Voice Dictation for ACF 的封面圖片
全新外掛
安裝啟用
尚無評分
剛更新
最後更新
問題解決
WordPress 6.0+ PHP 8.2+ v1.0.5 上架:2026-09-13

內容簡介

Speak Input 外掛為 Advanced Custom Fields (ACF) 增加了一個麥克風按鈕,讓編輯者及前端訪客可以透過語音輸入取代手動輸入,提升內容編輯的效率與便利性。

【主要功能】
• 語音轉文字功能,適用於文字及文本區域欄位
• 支援 Deepgram 作為轉錄引擎,需使用免費 API 金鑰
• 每個 ACF 欄位設定中可選擇啟用麥克風按鈕
• 自動根據編輯者的瀏覽器語言設定語音輸入語言
• Pro 版支援 WYSIWYG 欄位及 OpenAI 轉錄引擎

外掛標籤

開發者團隊

⬇ 下載最新版 (v1.0.5) 或搜尋安裝

① 下載 ZIP → 後台「外掛 › 安裝外掛 › 上傳外掛」
② 後台搜尋「Speak Input – Voice Dictation for ACF」→ 直接安裝(推薦)
📦 歷史版本下載

原文外掛簡介

Speak Input adds a microphone button to Advanced Custom Fields (ACF) so editors — and, where you allow it, front-end visitors — can dictate instead of type, in the WordPress admin or in any front-end form built with acf_form().
Click the microphone, speak, click again to stop. The recording is sent to your chosen speech-to-text engine and the transcript is inserted into the field a moment later — nothing is transcribed live while you speak, and nothing leaves your site until you stop recording.
Free

Voice dictation for text and textarea fields.
Deepgram as the transcription engine, using your own free Deepgram API key.
A dedicated “Speak Input” tab in every ACF field’s settings, so you choose exactly which fields get a microphone button — off by default.
Keyterm prompting: give Deepgram a list of names, jargon or product terms it should listen for.
Dictation language follows the editor’s browser language automatically.
Works in the admin and in front-end forms built with acf_form(), including for anonymous visitors, with a configurable request limit to protect your API usage.

Speak Input Pro
Pro unlocks:

Dictation for wysiwyg (rich text) fields, in addition to text and textarea.
A second transcription engine, OpenAI, selectable alongside Deepgram.
Insertion modes per field: replace the whole field, append, insert at the cursor, or replace only the current selection.
A configurable recording time limit per field.
A site-wide and per-field context prompt (used by the OpenAI engine) to improve accuracy for names, jargon or the topic of your site.
A fixed dictation language per field, with automatic WPML awareness.
A diagnostics screen: a log of transcription attempts (engine, result, timing) to help you troubleshoot and, if needed, share with support — never your dictated text or audio, only metadata.
Priority email support.

Find current Pro pricing and upgrade at speakinput.com/advanced-custom-fields.
“Speak Input Pro” is this plugin’s own paid tier — a separate product from “Advanced Custom Fields PRO”, the plugin this add-on extends. Speak Input, Free or Pro, works with either the free or the PRO version of Advanced Custom Fields.
Supported field types

Text
Textarea
WYSIWYG (rich text editor) — Pro

Transcription engines

Deepgram — Free and Pro. Requires your own Deepgram API key (a free tier is available).
OpenAI (gpt-transcribe) — Pro only. Requires your own OpenAI API key.

Privacy
Speak Input does not store your dictated audio. Recorded audio is sent to your chosen transcription engine for the sole purpose of producing a transcript, and is not retained by this plugin afterwards.
With Speak Input Pro, an optional diagnostics log records metadata about each transcription attempt — which engine was used, whether it succeeded, an error code if it failed, and how long it took — to help you troubleshoot issues or share details with support. This log never contains your dictated text or audio. It is stored in your own site’s database, has a configurable retention period, and can be cleared at any time from Settings > Speak Input ACF > Diagnostics.
External Services
Speak Input sends data to the following third-party services on your behalf. These calls only happen when you actively record and submit a dictation, or when the plugin checks your license — nothing is sent automatically or in the background.

Deepgram — when Deepgram is your selected engine, your recorded audio is sent to Deepgram’s API (using the API key you provide in Settings) to be transcribed, and the resulting text is returned to your site. Deepgram Terms of Service · Deepgram Privacy Policy
OpenAI (Pro only) — when OpenAI is your selected engine, your recorded audio is sent to OpenAI’s API (using the API key you provide in Settings) to be transcribed. OpenAI Terms of Use · OpenAI Privacy Policy
Freemius — used to manage licensing for the Pro version. If you activate a Pro license, basic site and plugin data (such as your site URL and WordPress/plugin version) is shared with Freemius to validate your license; no dictated audio or text is ever sent to Freemius. Freemius Terms of Service · Freemius Privacy Policy

Your API keys for Deepgram/OpenAI are stored in your site’s own database and are never exposed to site visitors or included in any front-end output. If visitors can dictate through a front-end acf_form(), you may want to mention Deepgram (and, on Pro, OpenAI) in your own site’s privacy policy, since their recorded audio is processed by that service.

延伸相關外掛

文章
Filter
Mastodon