[WordPress] 外掛分享： Sonoquill – AI Podcast Production

內容簡介

Sonoquill 是一款將書面文字轉換為完整播客集的外掛，使用者可透過自己的聲音克隆進行播報。它能自動重寫文本、檢查數據，並合成音頻，讓使用者專注於內容創作，最終生成可供發布的播客草稿。

【主要功能】
• 將文字轉換為播客音頻
• 自動重寫文本以適合聆聽
• 檢查數據的準確性
• 使用者可審核播報文本與音頻
• 提供聲音克隆功能
• 自動生成播客草稿

外掛標籤

開發者團隊

原文外掛簡介

Sonoquill turns written text into a finished podcast episode, spoken with your own voice clone. You keep writing — a fact script, a blog post, a page of your site — and Sonoquill does the rest: it rewrites the text for the ear, checks every number against your source, synthesises the audio, assembles music and chapters, has it mastered and hands you a ready Podlove draft.
Nothing goes online on its own. There are two human approvals: you approve the spoken text, and you approve the finished audio.
Sonoquill grew out of the monthly sky-preview podcast of an astronomy club, where it produces every episode. It is released as open source in the hope that it is useful to others.
How an episode is made

Source. Upload a DOCX, paste text, or pick a post or page of your site. Developers can add their own sources through a hook.
Spoken script. A language model (Anthropic Claude) rewrites the text for listening: numbers as words, spoken transitions, a fixed opening and sign-off. The prompts are editable, in German and English.
Checks. A deterministic number check compares every number, time and date of the source with the spoken script. A second model call looks for changed, missing or invented statements.
Your first approval. You read and edit the script in the browser. An e-mail tells you when it is waiting.
Voice. ElevenLabs speaks the script segment by segment with your voice clone. A pronunciation dictionary with phonetic (IPA) rules grows with every episode. Single passages can be re-recorded with your own voice.
Assembly. Pauses, opener, rotating music bridges between chapters, outro, chapter marks and a WebVTT transcript — with ffmpeg on your server, or in plain PHP with Auphonic adding the music.
Mastering and draft. Auphonic masters the episode; Sonoquill creates a Podlove draft with title, descriptions, chapters, transcript and an AI disclosure.
Your second approval. You listen and publish the episode in Podlove yourself.

Highlights

Numbers you can trust. The number check is plain code, not a model: a date that changed between source and script blocks the approval until you confirm it.
Your voice, your rules. Works with your own ElevenLabs voice clone. With Eleven v4, phonetic (IPA) pronunciation rules take effect in German and other languages, not only in English.
Transparent about AI. Every episode carries a disclosure in the show notes, optionally also spoken at the end.
Runs on ordinary hosting. No ffmpeg? Sonoquill joins the audio in PHP and lets Auphonic mix the music. Health checks show what works on your server.
Costs under control. Model calls can run through the Anthropic Batch API at half price, and every episode shows what its model calls cost.

Requirements

Podlove Podcast Publisher
API keys for Anthropic, ElevenLabs (with a voice clone you have the rights to) and Auphonic
An encryption key in wp-config.php: define('AASPF_ENCRYPTION_KEY', '…'); — 32 random bytes, base64 encoded. The settings page suggests one.
Optional: ffmpeg and exec() for mixing the music on your own server

Sonoquill is an open-source project without support. Bug reports and pull requests are welcome on GitHub.
External services
This plugin connects to the following services. Nothing is sent before you enter the corresponding API key, and each request happens only when the respective step runs (started by you or by the automatic chain you enabled).
Anthropic (Claude API)
Used to turn the fact script into a spoken script, to create title, descriptions and chapters, to check the spoken script against the source and to suggest pronunciation rules. Sent: the fact script, the spoken script, your prompts and the list of dictionary terms. Endpoint: api.anthropic.com.
Terms: https://www.anthropic.com/legal/commercial-terms — Privacy: https://www.anthropic.com/legal/privacy
ElevenLabs
Used for speech synthesis with your voice clone, for speech-to-speech re-recordings, to maintain the pronunciation dictionary and to show the remaining character quota. Sent: the spoken texts segment by segment, your re-recorded audio, dictionary rules. Endpoint: api.elevenlabs.io.
Terms: https://elevenlabs.io/terms-of-use — Privacy: https://elevenlabs.io/privacy-policy
Auphonic
Used to master the assembled episode and, without ffmpeg, to add opener, bridges and outro. Sent: the assembled audio, the music files, title, descriptions, keywords and chapter marks; Auphonic calls back a webhook URL of your site when the production is done. Endpoint: auphonic.com.
Terms: https://auphonic.com/terms_of_service — Privacy: https://auphonic.com/privacy