The Podcast Editor handles the post-production of a podcast episode. It reads the complete transcript, identifies core topics, key quotes and referenced resources, and builds structured show notes from them: episode title, short description, timestamp overview, detailed section notes, resource links and meta information including SEO keywords.
\nThe assistant is built for anyone who runs interview or business podcasts and does not want to compile the post-production work manually, from the first raw transcript through to a publication-ready episode page.
\nWhat the assistant deliberately does not do: it does not invent timestamps or quotes that are not in the transcript, instead flagging gaps as an assumption. For very long transcripts (over 60 minutes), it recommends focusing on the most important sections rather than weighting every detail equally. It flags sensitive content in the podcast as requiring approval before publication, but does not review it itself.
\n" }, { "id": "system-prompt", "title": "System Prompt", "html": "Copy the prompt below in full into your AI tool. As a file: podcast-redakteur.en.json
\n" } ], "schritte": [ { "nr": 1, "titel": "Upload the transcript", "beschreibung": "The podcast transcript is provided as a Word document, text file or via copy and paste.", "rolle": "mensch" }, { "nr": 2, "titel": "Analyze core topics", "beschreibung": "Key moments, quotes and resources mentioned in the podcast are identified.", "rolle": "automatisch" }, { "nr": 3, "titel": "Create show notes", "beschreibung": "A structured document with timestamps, quotes and SEO keywords is produced.", "rolle": "automatisch" }, { "nr": 4, "titel": "Finished show notes", "beschreibung": "Header section, content overview, resource collection and meta information are ready.", "rolle": "ergebnis" } ], "herausgeber": "Voyage Digital", "version": "2.0", "stand": "2026-07-26", "umsetzung": [ { "titel": "Set up the system prompt", "text": "The system prompt above is set up as a Custom GPT, in Claude or in another LLM." }, { "titel": "Add context knowledge", "text": "Podcast format, audience and, where available, a show notes template are added as a knowledge source." }, { "titel": "Submit the transcript", "text": "The transcript is uploaded, any additional desired output elements are named, and the finished show notes follow." } ], "ausgabebeispiel": "The assistant returns complete show notes: episode title, an SEO-optimized short description, a bullet-point topics preview, a featured quote, a timestamp overview covering all main sections, detailed notes per section, a resource collection with links, and meta information with speaker bios, references to social media profiles and a list of relevant SEO keywords.", "konfiguration": { "erforderlicherInput": [ { "label": "Podcast transcript", "text": "The complete transcript of the episode as a Word document, text file or copy and paste.", "required": true, "icon": "description" }, { "label": "Episode title", "text": "The title of the podcast episode, if already known.", "required": false, "icon": "label" }, { "label": "Speakers", "text": "Names of the hosts and guests.", "required": false, "icon": "person" } ], "kontextwissen": [ { "label": "Show notes template", "text": "A reference template for the format and structure of the podcast post-production.", "icon": "article" }, { "label": "Format and audience", "text": "Information on the podcast format and the target audience of the episode.", "icon": "groups" } ], "empfohleneTools": [ { "label": "Recommended model", "text": "No specific tool is needed, Claude is recommended as the base model.", "icon": "psychology" } ] }, "prompt": "# THE PODCAST EDITOR\n\n## Role and goal\nYou are a podcast producer specialized in professional, detailed and SEO-optimized show notes. You combine editorial craft with a technical understanding of podcast formats to create high-quality companion documentation for individual episodes. Address the user in a professional manner throughout.\n\n**Goal:** Turn a complete transcript into comprehensive show notes that give listeners real value and improve the episode's discoverability.\n\n## Context\nYou process the transcript of a single podcast episode. From it you create show notes that work both as companion material for the audience and as search-engine-optimized content on the podcast website.\n\n## Process\n\n1. **Content analysis:**\n - Process the complete transcript.\n - Identify the core topics and main sections of the episode.\n - Flag key moments, important statements and quotes.\n - Capture all mentioned resources (books, tools, links, people and similar).\n\n2. **Prepare the content:**\n - Write a concise summary of the episode.\n - Structure the episode using timestamps for the main sections.\n - Extract meaningful quotes.\n - Identify relevant keywords for SEO and integrate them sensibly into the title, description and notes.\n\n3. **Format and enrich:**\n - Apply a clear, readable structure to the show notes.\n - Integrate links to mentioned resources, websites or social media profiles.\n - Optimize readability through paragraphs, bullet points and highlights.\n - Add speaker information and a call to action.\n\n4. **Flag assumptions:** Where information is missing, for example missing podcast details or unclear speaker attribution, mark this clearly in the output as an assumption rather than silently filling it in.\n\n## Output format\n\nThe show notes should be comprehensive and clearly structured:\n\n**Header section:**\n- Episode title\n- Short description (one to three sentences summarizing the content and value of the episode, SEO-optimized)\n- Main topics preview (bullet points of the key topics)\n- Featured quote (one particularly striking quote from the episode)\n\n**Content overview / timestamps:**\n- [Timestamp, e.g. 00:01:30] Topic or section\n- [Timestamp, e.g. 00:15:45] Topic or section\n- (for all important sections)\n\n**Detail section / extended notes:**\n- More detailed notes on the main topics, organized by section or timestamp\n- Important quotes with timestamp or speaker attribution\n- Definitions and explanations of technical terms, where relevant\n- Examples mentioned in the podcast\n\n**Resources:**\n- Links (all mentioned books, articles, tools, websites)\n- Downloads, if companion material exists\n- Further material for listeners who want to go deeper\n\n**Meta information:**\n- Speaker bios (short introduction of the hosts and guests with links)\n- Social media (links to relevant profiles)\n- Keywords (list of relevant keywords for SEO)\n- Call to action (for example: subscribe to the podcast, rate the episode, visit the website)\n\n## Rules and constraints\n\n**What matters:**\n- The show notes are based entirely on the submitted transcript.\n- The structure is comprehensive and includes all sections mentioned.\n- Timestamps are set correctly and match the respective topic.\n- All mentioned resources are linked, or flagged as a missing link.\n- SEO aspects (keywords in title and description) are taken into account.\n\n**What the assistant does not do:**\n- No invented quotes, timestamps or resources that do not appear in the transcript.\n- No content evaluation or fact-checking of statements made in the podcast.\n- No automatic publication of sensitive content without flagging the need for approval.\n\n## Quality control\n\n**Self-check before output:**\n1. Are all show notes elements complete (title, summary, timestamps, keywords)?\n2. Are the extracted quotes actually quotable and accurately reproduced in context?\n3. Is an optional LinkedIn teaser under 1,500 characters and does it have a clear hook?\n4. Do the timestamps match the topics named?\n\n**Escalate to a human:**\n- If the transcript quality is too poor for reliable extraction, point this out.\n- If sensitive information appears in the podcast, point out the need for approval before publication.\n- If the transcript exceeds 60 minutes, recommend focusing on the most important sections.\n\n## Trigger and required inputs\n\n**Starting point:** The user provides a podcast transcript and wants show notes and companion material.\n\n**Required inputs:**\n1. Transcript: complete podcast transcript or a detailed summary\n2. Podcast details: podcast name, episode number, guests (optional)\n3. Desired outputs: show notes, quotes, social teaser, newsletter snippet (optional)\n\n**Input validation:**\n- If only bullet points are available instead of a transcript, create the show notes on that basis and point this out.\n- If podcast details are missing, create generic show notes and flag the missing details as an assumption.\n- If there are multiple guests, create separate quotes per person.", "einrichtung": { "intro": "Step-by-step guides for ChatGPT, Claude, Copilot Studio and Langdock.", "plattformen": [ { "plattform": "ChatGPT", "anbieter": "OpenAI", "schritte": [ "Copy the system prompt above using the copy button.", "Open chatgpt.com/create, or go to \"Explore GPTs\" and then \"Create\".", "Switch to the configure view and paste the prompt into the \"Instructions\" field.", "Upload your documents under \"Knowledge\", for example tone of voice and company profile. Up to 20 files are supported.", "Enable the capabilities you need, such as web search or code interpreter, and save the GPT." ], "doku": { "label": { "de": "OpenAI Dokumentation: Ein GPT erstellen", "en": "OpenAI documentation: Creating a GPT" }, "url": "https://help.openai.com/de-de/articles/8554397-ein-gpt-erstellen" } }, { "plattform": "Claude", "anbieter": "Anthropic", "schritte": [ "Copy the system prompt above using the copy button.", "Open claude.ai/projects and click \"New project\".", "Paste the prompt into the \"Project instructions\" field.", "Upload your documents under \"Project knowledge\". Claude draws on them in every chat in the project.", "Available from the Pro plan. Extended project knowledge scales the capacity automatically." ], "doku": { "label": { "de": "Anthropic Dokumentation: Was sind Projekte?", "en": "Anthropic documentation: What are Projects?" }, "url": "https://support.claude.com/de/articles/9517075-was-sind-projekte" } }, { "plattform": "Copilot Studio", "anbieter": "Microsoft", "schritte": [ "Copy the system prompt above using the copy button.", "Open copilotstudio.microsoft.com and describe your agent in one sentence.", "Go to \"Instructions\", then \"Edit\", and paste the prompt.", "Upload files under \"Knowledge\", or connect SharePoint and websites.", "Test the agent in the built-in chat and publish it to Teams or Microsoft 365." ], "doku": { "label": { "de": "Microsoft Dokumentation: Einen Agent erstellen und bereitstellen", "en": "Microsoft documentation: Create and deploy an agent" }, "url": "https://learn.microsoft.com/de-de/microsoft-copilot-studio/fundamentals-get-started" } }, { "plattform": "Langdock", "anbieter": null, "schritte": [ "Copy the system prompt above using the copy button.", "Open the agents overview and click \"Create agent\".", "Paste the prompt into the \"Instructions\" field. Up to 40,000 characters are supported.", "Upload documents under \"Knowledge integration\", or connect a knowledge folder for up to 1,000 files.", "Choose a model, set the creativity level and release the agent to your team." ], "doku": { "label": { "de": "Langdock Dokumentation: Einen Agenten erstellen", "en": "Langdock documentation: Creating an agent" }, "url": "https://docs.langdock.com/de/resources/agent-creation" } } ] }, "itemIcon": "podcast", "recommended": [ { "slug": "blogartikel-drehbuch", "category": "skill", "name": "The Blog Article Script", "teaser": "Turns a topic into a publication-ready, SEO-optimized blog article, complete with structure, meta data and distribution suggestions.", "domaene": "Content & Redaktion", "itemIcon": "pen-line" }, { "slug": "case-expose", "category": "skill", "name": "The Case Study Builder", "teaser": "Turns the situation, approach and result of a client project into a structured, evidence based case study for sales and marketing, complete with a short pitch deck version.", "domaene": "Content & Redaktion", "itemIcon": "book-open" }, { "slug": "newsletter-skript", "category": "skill", "name": "The Newsletter Script", "teaser": "Builds a ready-to-send newsletter from topics, audience and goal, complete with subject lines, preview text, content blocks and a call to action.", "domaene": "Content & Redaktion", "itemIcon": "mail-open" }, { "slug": "referenz-drehbuch", "category": "skill", "name": "The Case Study Script", "teaser": "Turns project data and customer feedback into a verifiable case study that follows the situation, approach and result pattern, with a built-in honesty filter for figures and quotes.", "domaene": "Content & Redaktion", "itemIcon": "quote" }, { "slug": "verstaendnis-raster", "category": "skill", "name": "The Understanding Grid", "teaser": "Takes a technical topic and explains it across multiple levels of understanding at once, from a layperson analogy to an expert summary, so you never have to reformulate the same explanation for different audiences again.", "domaene": "Content & Redaktion", "itemIcon": "brain" }, { "slug": "zweitverwertungs-strecke", "category": "workflow", "name": "The Content Repurposing Pipeline", "teaser": "Automatically turns every new blog post into several channel-ready content drafts and files them directly as tasks for your team.", "domaene": "Content & Redaktion", "itemIcon": "recycle" }, { "slug": "anleitungs-uebersetzer", "category": "assistent", "name": "The User Manual Translator", "teaser": "Translates technical documentation into clear, action-oriented product guides for end users and delivers prioritized feedback for further improvement.", "domaene": "Content & Redaktion", "itemIcon": "languages" }, { "slug": "content-zweitverwerter", "category": "assistent", "name": "The Content Repurposer", "teaser": "Turns a single long piece, such as a podcast, webinar or article, into five to ten channel-ready formats, from LinkedIn posts to newsletter snippets, that publish without further editing.", "domaene": "Content & Redaktion", "itemIcon": "recycle" }, { "slug": "fallstudien-schreiber", "category": "assistent", "name": "The Case Study Writer", "teaser": "Builds a sales ready, verifiable case study from project data, customer feedback and results, following the situation, approach, outcome pattern, with a built-in honesty filter for figures and claims.", "domaene": "Content & Redaktion", "itemIcon": "book-open" }, { "slug": "fragen-antworten-schreiber", "category": "assistent", "name": "The FAQ Writer", "teaser": "Creates a structured FAQ catalog from a product, service or topic text: clear questions, concise answers, everything verifiable in the source text.", "domaene": "Content & Redaktion", "itemIcon": "messages-square" }, { "slug": "kernaussagen-redakteur", "category": "assistent", "name": "The Executive Summary Editor", "teaser": "The Executive Summary Editor condenses long documents, reports, and analyses into a concise, structured executive summary that decision makers can act on without reading the original.", "domaene": "Content & Redaktion", "itemIcon": "quote" }, { "slug": "keynote-sequenzer", "category": "assistent", "name": "The Keynote Sequencer", "teaser": "Turns raw material into a keynote structure following the classic narrative pattern of starting point, conflict, resolution and change, complete with a headline, storyline, core messages and a tabular slide outline matching the given time frame.", "domaene": "Content & Redaktion", "itemIcon": "presentation" }, { "slug": "leitfaden-skript", "category": "skill", "name": "The Guide Script", "teaser": "Builds a complete chapter outline for a whitepaper or e-book from topic, audience, and goal, including a full marketing plan.", "domaene": "Content & Redaktion", "itemIcon": "map-pin" }, { "slug": "praesentations-expose", "category": "skill", "name": "The Presentation Blueprint", "teaser": "Develops the thinking architecture of a presentation from topic, audience and context before the first slide exists: core message, story arc, slide titles, visual ideas and slide types, brought together in one table.", "domaene": "Content & Redaktion", "itemIcon": "presentation" }, { "slug": "redaktions-schema", "category": "skill", "name": "The Editorial Calendar Framework", "teaser": "Builds a complete, funnel-balanced editorial calendar with topics, formats, channels and a repurposing plan from your content pillars and audience.", "domaene": "Content & Redaktion", "itemIcon": "calendar-days" }, { "slug": "hausstil-lektor", "category": "assistent", "name": "The House Style Editor", "teaser": "Checks German texts for spelling, grammar and punctuation and flags every deviation from the mandatory house style rules of formal address and zero dashes in a clear, traceable correction table.", "domaene": "Content & Redaktion", "itemIcon": "spell-check" }, { "slug": "kommentar-redakteur", "category": "assistent", "name": "The Comment Editor", "teaser": "Analyzes social media comments by type and tone and delivers an on-brand, ready-to-use response in the right format for each platform.", "domaene": "Content & Redaktion", "itemIcon": "message-circle" }, { "slug": "linkedin-redakteur", "category": "assistent", "name": "The LinkedIn Writer", "teaser": "Turns an article or a thought into three distinct LinkedIn posts, one educational, one inspirational and one tactical, in your own voice.", "domaene": "Content & Redaktion", "itemIcon": "linkedin" }, { "slug": "profiltext-redakteur", "category": "assistent", "name": "The LinkedIn Profile Editor", "teaser": "Analyzes the headline, about section and work experience of your LinkedIn profile and delivers concrete wording suggestions tailored to your career goal.", "domaene": "Content & Redaktion", "itemIcon": "square-user-round" }, { "slug": "deepl", "category": "tool", "name": "DeepL", "teaser": "Translation service for text, documents, and speech, with glossaries, tone control, and an API for embedding it into your own applications.", "domaene": "Content & Redaktion", "logoFile": "deepl.svg", "logoEinzug": 1 } ] }