Batch-generate images via OpenAI Images API using a random prompt sampler and an `index.html` gallery for easy viewing.
Podcast Episode Show Notes and Transcript Synchronizer
This skill automatically discovers speaker changes, topic shifts, and key discussion points within podcast audio. It produces a comprehensive, time-stamped transcript, SEO-friendly show notes with summaries, key takeaways, and relevant links, and a list of discussion topics. The skill verifies the accuracy of the transcript against the audio, ensures timestamps align with spoken content, and checks show notes for factual consistency with the episode. It keeps the show notes and transcript current by detecting changes in the audio file and automatically updating the corresponding text, maintaining perfect synchronization. It never invents unverified details, flagging any unclear audio segments or unconfirmed external references.
What It Does
This skill automatically discovers speaker changes, topic shifts, and key discussion points within podcast audio. It produces a comprehensive, time-stamped transcript, SEO-friendly show notes with summaries, key takeaways, and relevant links, and a list of discussion topics. The skill verifies the accuracy of the transcript against the audio, ensures timestamps align with spoken content, and checks show notes for factual consistency with the episode. It keeps the show notes and transcript current by detecting changes in the audio file and automatically updating the corresponding text, maintaining perfect synchronization. It never invents unverified details, flagging any unclear audio segments or unconfirmed external references.
The Problem It Removes
The recurring pain of manually transcribing podcast episodes, extracting key topics, writing engaging show notes, and precisely time-stamping segments is extremely labor-intensive and error-prone.
The real cost includes significant hours spent by producers or assistants, delayed episode releases, and reduced discoverability due to poor SEO in show notes. This leads to missed audience growth opportunities and inefficient content repurposing.
This skill removes the entire manual workflow of post-production text generation, ensuring high-quality, synchronized content is ready for publication immediately after audio finalization. It frees up valuable human resources to focus on content creation and strategy.
Who It Is For
This skill is for podcast producers, content marketers, audio editors, and media companies who need to efficiently manage and publish podcast content.
Especially valuable when:
- Podcasters releasing frequent episodes who need to streamline post-production.
- Media companies aiming to improve accessibility and SEO for their audio content.
- Educational podcasters requiring detailed transcripts and notes for learners.
- Content marketers repurposing audio into blog posts or articles.
- Teams needing to ensure compliance with accessibility standards for audio content.
- Anyone who needs to quickly search or reference specific parts of an episode.
- Producers who want to reduce the manual effort and errors associated with text asset generation.
Why This Price
The recurring pain of manually transcribing podcast episodes, extracting key topics, writing engaging show notes, and precisely time-stamping segments is extremely labor-intensive and error-prone. This process can consume several hours per episode, diverting valuable time from content creation and strategic planning.
The real cost includes significant hours spent by producers or assistants, delayed episode releases, and reduced discoverability due to poor SEO in show notes. This leads to missed audience growth opportunities and inefficient content repurposing, directly impacting a podcast's reach and monetization potential.
This skill removes the entire manual workflow of post-production text generation, ensuring high-quality, synchronized content is ready for publication immediately after audio finalization. It frees up valuable human resources to focus on content creation and strategy, providing a compounding return on investment with every episode published. Buyers pay for the automation of a complex, recurring task, the assurance of accuracy and synchronization, and the enhanced discoverability that drives audience growth.
One payment, yours permanently. Download it again at any time and get later versions free.
How It Differs From Similar Skills
Existing skills like openai-whisper and openai-whisper-api provide basic audio transcription but do not extend to generating structured show notes, identifying topics, applying SEO best practices, or handling synchronization with audio edits. audio-transcriber is also a basic transcription skill. These tools offer a raw component, not a finished product.
This skill performs the operational job of taking raw audio and producing a fully formatted, SEO-optimized, and continuously synchronized text package. It integrates transcription with content analysis, SEO, and ongoing maintenance, which is a distinct and more comprehensive job than simple audio-to-text conversion. No other skill provides this end-to-end, verified, and synchronized solution.
When To Use
- A podcast producer has just finalized an audio edit and needs all accompanying text assets generated and synchronized before publishing.
- A content marketer wants to repurpose a podcast episode into blog posts and needs a precise, searchable transcript and key takeaways.
- An audio editor needs to ensure that any last-minute changes to an episode's audio are immediately reflected in its show notes and transcript.
- A media company is preparing to launch a new podcast series and requires a scalable, automated solution for post-production text generation.
- An educational podcaster needs to provide learners with accurate, time-stamped transcripts and summaries for study and reference.
Inputs
podcastAudioFile: The audio file of the podcast episode (e.g., MP3, WAV). (episode-012-interview-with-dr-smith.mp3)
episodeBrief: An optional document or text containing episode context, key discussion points, guest names, and external links. (Guest: Dr. Jane Smith, Topic: AI in Healthcare, Links: example.com/dr-smith-book)
Outputs
showNotes: SEO-optimized show notes with episode summary, key takeaways, discussion topics, and relevant links. (Markdown table or HTML)
transcript: A comprehensive, time-stamped, and speaker-identified transcript of the entire podcast episode. (Plain text or Markdown)
discussionTopics: A list of key discussion topics identified in the episode with their corresponding timestamps. (JSON object or Markdown list)
How It Works From Start To Finish
- Receive podcast audio file and episode brief.
- Transcribe audio, identifying speakers and segmenting dialogue.
- Analyze transcript for key topics, discussion points, and calls to action.
- Generate precise timestamps for each topic and key moment.
- Draft SEO-optimized show notes, including summary, takeaways, and links.
- Format full transcript for readability and accessibility.
- Verify timestamp accuracy against the audio.
- Check show notes for factual consistency with episode content.
- Flag any unclear audio or unverified external references.
- Output show notes and transcript in publishable formats (e.g., markdown, HTML).
- Detect audio file re-edits and update corresponding text content.
What you supply
- Podcast audio file (MP3, WAV)
- Optional episode brief
What it finds out on its own
- Spoken content
- Speaker changes
- Topic shifts
- Key phrases
- Natural pauses
- Episode duration
Step By Step
-
Ingest Audio and Brief
Receive the podcast audio file and any optional episode brief.
Done when: The audio file and brief (if provided) are successfully loaded and accessible.
If it cannot finish: Report failure to access or load files and terminate.
-
Transcribe and Analyze Audio
Process the audio file using a speech-to-text model to generate a raw transcript, identify speaker changes, segment dialogue, and extract key topics, discussion points, and relevant keywords.
Done when: A raw transcript with speaker labels, initial segment timings, and a structured list of topics and keywords is generated, along with confidence scores for each segment.
If it cannot finish: If audio quality is too poor, flag specific segments with low confidence and provide a partial transcript, highlighting areas for human review. Report inability to extract meaningful topics and proceed with a basic summary.
-
Generate Timestamps and Draft Show Notes
Create precise timestamps for each identified topic shift, speaker change, and key moment, aligning them with the audio. Draft SEO-optimized show notes including a summary, key takeaways, relevant links (from brief or discovered), and discussion topics.
Done when: A list of time-stamped segments is generated, and a draft of the show notes is created, incorporating SEO best practices and all extracted information.
If it cannot finish: Report any segments where precise timestamp alignment could not be achieved and mark them for manual review. Generate basic show notes with available information, flagging missing elements.
-
Format Transcript and Show Notes
Format the full transcript for readability and accessibility, adding speaker labels and clear paragraph breaks. Refine the show notes for clarity and publishable quality.
Done when: The full transcript is formatted into a clean, readable text document, and the show notes are polished and ready for verification.
If it cannot finish: Output the raw transcript and unrefined show notes as-is.
-
Verify All Text Assets
Cross-reference generated timestamps against the audio content for accuracy. Check show notes for factual consistency with the episode content in the transcript and validate all external links.
Done when: All timestamps are verified to be within a 1-second margin of error. Show notes accurately summarize episode content, key takeaways are present, and all external links are functional and relevant. Any unverified details are marked unresolved.
If it cannot finish: Flag any misaligned timestamps, factual inconsistencies, broken links, or unverified external references, marking them as "unresolved" and reporting the discrepancy.
-
Output Final Publishable Assets
Produce the verified show notes and transcript in publishable formats (e.g., Markdown, HTML, plain text).
Done when: The final show notes and transcript files are generated and saved in the specified formats.
If it cannot finish: Report failure to generate output files and provide the raw text content.
-
Monitor and Synchronize Audio Changes
Implement a mechanism to detect changes in the original podcast audio file. If an audio file re-edit is detected, automatically re-process the affected segments to update the transcript and show notes.
Done when: The audio file's state is continuously monitored for modifications, and text assets are automatically re-generated and synchronized upon detection of changes.
If it cannot finish: Report inability to set up continuous monitoring or failure to re-synchronize, flagging the discrepancy between audio and text assets.
How It Checks Its Own Work
Checks before it delivers
- All spoken words in the audio are present in the transcript.
- Timestamps accurately reflect the start time of corresponding audio segments.
- Show notes accurately summarize episode content and key takeaways.
- External links in show notes are functional and relevant.
- No unverified information is added to notes or transcript.
If something goes wrong
- If audio quality is too poor for accurate transcription, it reports the specific segments with low confidence and provides a partial transcript, highlighting areas for human review.
- If an external link provided in the brief is broken, it flags the broken link and suggests alternatives or marks it as "unresolved: broken link".
Mistakes It Prevents
| The mistake | What it costs | How the skill prevents it |
|---|---|---|
| Manually transcribing audio, leading to frequent typos, mishearings, or omissions. | Inaccurate transcripts frustrate listeners, misrepresent episode content, and undermine the podcast's credibility. | Automated transcription with a confidence score for each segment, flagging low-confidence areas for human review. |
| Adding timestamps inconsistently or inaccurately during manual show note creation. | Listeners cannot easily navigate the episode, missing key discussions, which reduces engagement and perceived value. | Automatic generation of timestamps tied to detected topic shifts and speaker changes, verified for precise audio alignment. |
| Writing generic show notes that lack specific keywords, clear summaries, or actionable takeaways. | Episodes are less discoverable in search engines, limiting audience growth and the potential for content repurposing. | Automated analysis of transcript content to identify relevant keywords, main discussion points, and calls to action for SEO-optimized summaries. |
| Failing to update show notes or transcripts after a podcast audio file has been re-edited or corrected. | Discrepancies between the audio and text assets confuse listeners, lead to complaints, and erode content integrity. | Implementing a change detection mechanism that automatically triggers re-processing and synchronization of text assets upon audio file modification. |
| Including factual errors or unverified external links in show notes without proper checks. | Damages the podcast's reputation, misinforms the audience, and leads to broken user experiences. | Cross-referencing show note claims with transcript content and automatically validating external links, flagging any unverified or broken elements. |
Edge Cases It Handles
- Manually transcribing audio, leading to frequent typos, mishearings, or omissions.
- Automated transcription with a confidence score for each segment, flagging low-confidence areas for human review.
- Adding timestamps inconsistently or inaccurately during manual show note creation.
- Automatic generation of timestamps tied to detected topic shifts and speaker changes, verified for precise audio alignment.
- Writing generic show notes that lack specific keywords, clear summaries, or actionable takeaways.
- Automated analysis of transcript content to identify relevant keywords, main discussion points, and calls to action for SEO-optimized summaries.
- Failing to update show notes or transcripts after a podcast audio file has been re-edited or corrected.
- Implementing a change detection mechanism that automatically triggers re-processing and synchronization of text assets upon audio file modification.
- Including factual errors or unverified external links in show notes without proper checks.
- Cross-referencing show note claims with transcript content and automatically validating external links, flagging any unverified or broken elements.
- Audio quality is too poor for accurate transcription.
- Reports specific segments with low confidence and provides a partial transcript, highlighting areas for human review.
- An external link provided in the brief is broken.
- Flags the broken link and suggests alternatives or marks it as "unresolved: broken link".
A Worked Example
A podcast producer has just finished editing an interview episode about sustainable urban farming and needs to publish it with full text assets.
Input
podcastAudioFile: "urban-farming-future-ep45.mp3", episodeBrief: "Guest: Dr. Anya Sharma, Topic: Vertical Farming Innovations, Key points: hydroponics, aeroponics, community gardens. Links: example.com/anya-sharma-research, example.com/urban-farm-guide"
Expected output
showNotes: # Episode 45: The Future of Urban Farming with Dr. Anya Sharma
## Summary
In this insightful episode, we delve into the world of sustainable urban farming with leading expert Dr. Anya Sharma. We explore groundbreaking innovations like vertical farming, hydroponics, and aeroponics, discussing their potential to revolutionize food production in cities. Dr. Sharma also shares her perspectives on the role of community gardens and policy changes needed for a greener urban future.
## Key Takeaways
* Vertical farming offers significant space and water efficiency benefits for urban environments.
* Hydroponics and aeroponics are key technologies enabling soil-less cultivation.
* Community gardens foster local food security and social cohesion.
* Policy support is crucial for scaling urban agriculture initiatives.
## Discussion Topics
* [00:02:15] Introduction to Dr. Anya Sharma and her work
* [00:07:30] The rise of vertical farming and its advantages
* [00:15:00] Deep dive into hydroponics vs. aeroponics
* [00:22:40] The social impact of community gardens
* [00:31:00] Policy and investment needed for urban agriculture
* [00:40:10] Future outlook and listener questions
## Resources
* Dr. Anya Sharma's Research: [example.com/anya-sharma-research](example.com/anya-sharma-research)
* Urban Farming Guide: [example.com/urban-farm-guide](example.com/urban-farm-guide)
transcript: (A full, time-stamped transcript of the 45-minute episode, formatted for readability, with speaker labels like "Speaker 1: Hello, and welcome..." and "[00:02:15] Speaker 2: Thank you for having me...")
Why this output: The skill processed the audio and brief, accurately transcribed the conversation, identified key topics, generated precise timestamps, and crafted SEO-optimized show notes. It ensured all provided links were functional and that the summary and takeaways reflected the actual episode content, providing a complete, synchronized package for publication.
Keeping It Current And Knowing Its Limits
Keeping it current
If the podcast audio file is updated (e.g., for re-edits or corrections), the skill automatically re-processes the affected segments to update the transcript and show notes, maintaining perfect synchronization.
What it will not do
- It will not invent episode content or external links not provided in the brief or discoverable from the audio.
- It cannot verify the subjective quality of the podcast content itself.
- It requires read access to audio files.
- It never invents unverified details.
- It will not modify existing human-written content without explicit instruction or clear indication of changes.
Limitations
Installation
Configure in .aider.conf.yml
Copy to ~/.claude/skills/
Add to Cline skills directory
Add to .cursor/skills/
Add to ~/.gemini/skills/
Add to Copilot workspace settings
Configure in API settings
Add to .vscode/skills/
Add to Windsurf skills
Before You Run It
Security notes
- This skill requires read access to your podcast audio files to perform transcription and analysis.
- It may perform outbound network requests to validate external links provided in the episode brief or discovered during analysis.
- The skill is designed to flag unverified details rather than invent them, reducing the risk of misinformation.
- It will not modify existing human-written content without explicit instruction.
Questions People Ask
How accurate are the transcripts generated by this skill?
The skill uses advanced speech-to-text models and includes a verification step to cross-reference against the audio. It also flags segments with low confidence for potential human review, ensuring high accuracy while transparently identifying any challenging areas.
Can this skill handle multiple speakers in a podcast episode?
Yes, the skill is designed to identify speaker changes and segment dialogue, providing a transcript with speaker labels for clarity. This helps in distinguishing who said what throughout the episode.
What happens if I re-edit my podcast audio after generating the notes and transcript?
The skill includes a continuous monitoring mechanism. If it detects changes in your original podcast audio file, it will automatically re-process the affected segments and update the transcript and show notes to maintain perfect synchronization.
Will the show notes be optimized for search engines?
Absolutely. The skill analyzes the transcript content to identify relevant keywords, main discussion points, and calls to action, using these to craft SEO-optimized summaries and key takeaways that enhance discoverability.
What if an external link I provided in the episode brief is broken?
The skill performs validation checks on all external links. If a broken link is detected, it will be flagged and marked as "unresolved: broken link" in the output, allowing you to address it before publication.
What people say, and where to get help
No ratings yet. If you have used this skill, yours would be the first.
Sign in to leave a rating
An account keeps your review with your name on it, and lets you edit it later. Sign in or create one free.
No reviews yet
This skill has not been rated. If you have run it, a short note about what you used it for helps the next person more than any description can.
Related Skills You May Like
Discover more AI agent skills in the same category to enhance your workflow automation.
Generate spectrograms and feature-panel visualizations from audio using the songsee CLI tool.
Local text-to-speech conversion using sherpa-onnx, enabling offline and private TTS functionality without relying on cloud services.
Transcribe audio to text locally using the OpenAI Whisper CLI tool, without requiring an API key.
ElevenLabs text-to-speech with a Mac-style 'say' UX, enabling quick audio generation and playback from the command line.
Transcribe audio files using OpenAI's Whisper API via a simple bash script, requiring an OpenAI API key.
Have a Skill to Share?
Join the community and help AI agents learn new capabilities. Submit your skill and reach thousands of developers.