Not a transcription tool.
An intelligent content platform.

Turn massive volumes of audio and video
into structured professional deliverables.
8 tabs. One pipeline. AI at every step.

An AI Guide helps you plan the perfect workflow. A Custom Prompt Engine designs the perfect extraction. AI Curation scores and sorts everything. You approve.

Researchers Lawyers Medical Professionals Course Creators Authors Filmmakers Journalists Students
1

Extract

Paste URLs from 8 platforms. Import entire channels, playlists, or paste 100+ URLs at once. XTC downloads the audio and queues everything for processing.

Y

YouTube

Videos, channels, playlists. Set range bounds.

I

Instagram

Reels, stories, IGTV.

T

TikTok

Any public TikTok URL.

X

X (Twitter)

Spaces, video, voice tweets.

V

Vimeo

Public and unlisted videos.

S

Spotify

Podcast episodes.

P

Podcasts

RSS feeds, direct episode URLs.

F

Local Files

MP3, MP4, WAV, M4A, more.

Extract tab with bulk URL import
2

Transcribe

Four engines from fast drafts to studio-grade accuracy. AI-powered speaker diarization separates voices automatically. 90+ languages supported.

Fast Draft

Whisper tiny/base. Fastest turnaround.

  • Speed Fastest
  • Quality Good
  • Cost Free (local)

Studio Quality

Whisper medium/large. Balanced.

  • Speed Moderate
  • Quality High
  • Cost Free (local)

Studio Pro

Whisper large-v3 with diarization.

  • Speed Slower
  • Quality Highest (local)
  • Cost Free (local)

AssemblyAI

Cloud engine. Native diarization.

  • Speed Fast
  • Quality Highest
  • Cost Pay-per-use
Transcribe tab with speaker diarization
3

Correct

AI-powered transcript cleanup. Fix transcription errors, rename speakers, remove filler words, and merge segments. Integrated waveform editor for precise fixes when you need to verify against the audio.

Correct tab with waveform editor and AI cleanup
4

Subtract

Remove the noise before you extract the signal. Strip intros, ads, outros, filler segments, and anything else that dilutes your source material.

Subtract tab filtering out ads and intros
5

Organize

Semantic clustering groups hundreds of extractions into topics automatically. No manual sorting. Related quotes, insights, and dialogues land together.

Choose your LLM

Three providers. Your API keys. Pick the model that fits your budget and quality needs.

Claude (Anthropic)

Best for nuanced extraction and long-form content. Excellent at preserving voice and tone.

Haiku 3 ($) Sonnet ($$) Opus ($$$)

OpenAI

Reliable extraction with strong instruction following. Great all-rounder.

GPT-4o-mini ($) GPT-4o ($$)

Grok (xAI)

Fast, capable models from xAI. Growing model lineup.

Grok models
Organize tab with semantic clusters
6

Select

Keyboard-driven curation built for speed. Review extractions, keep the diamonds, discard the rest. Process hundreds of results in minutes, not hours.

Select tab with keyboard curation interface
7

Compose

This is where XTC goes from extraction tool to book-writing pipeline. AI drafts full book chapters from your curated selections. Hierarchical outline editor, side-by-side preview, and real-time generation.

Compose tab with outline editor and side-by-side preview
8

Publish

Export your work in six formats. Whether you need raw data for a pipeline, polished chapters for a publisher, or structured notes for your CMS.

.md
.json
.txt
.pdf
.docx
.csv

Prompt Library

25+ built-in extraction prompts across 5 categories. Write your own. Refine until it is right. Save as presets.

Quotes

Theme Quotes, Punchy/Short, Quote+Context, Actionable, Contrarian/Insight

Dialogues

Best Exchanges, Q&A Highlights, Conflict/Tension

Book English

Rewrite spoken content as polished, publishable prose

Remove Labels

Strip speaker labels and timecodes for clean output

User Presets

Your saved custom prompts, reusable across sessions

Custom

Write your own extraction logic. Iterate until output matches your needs.

Prompt refining

Run an extraction, review the output, adjust your prompt, run again. Iterate until the results are exactly what you need. No guessing.

Cost preview

See the estimated LLM cost before running any extraction. Strict fidelity toggle keeps extractions close to the original wording when accuracy matters most.

The Intelligence Layer

Seven AI-powered capabilities that turn XTC Studio from a pipeline into a thinking partner. Every feature runs locally, works offline, and respects your data.

G

AI Guide

Describe what you need in plain language. The AI Guide interviews you, understands your goal, and plans the entire pipeline: which sources to pull, which transcription engine to use, what extraction prompts to run, and how to organize the output.

For beginners

No need to learn the 8-tab pipeline. Tell the Guide what you want, and it configures everything for you.

For power users

Skip the manual setup on complex projects. Describe the deliverable, review the plan, hit go.

D

Dual Extraction Modes

Two fundamentally different ways to process content. Preserve mode keeps exact words for books and legal work. Distill mode extracts ideas, themes, and insights for research and course creation.

Preserve Mode

Exact words. Faithful to the source. Every quote, every phrase, every nuance stays intact. Built for authors compiling books from spoken material, lawyers needing verbatim testimony, and journalists who need the real words.

  • Verbatim extraction with speaker attribution
  • Context markers so you know where each block came from
  • Strict fidelity scoring to flag any AI paraphrasing

Distill Mode

Extract the signal, not the noise. AI identifies core ideas, synthesizes themes across sources, and produces clean, structured insights. Built for researchers, course creators, and anyone turning hours of content into knowledge.

  • Idea extraction across multiple sources
  • Theme synthesis and pattern detection
  • Structured output: frameworks, key takeaways, action items
C

AI Curation

AI scores every extracted block from 1 to 5 and recommends Keep, Star, or Trash. It explains its reasoning so you stay in control. Style-aware: it curates differently for a legal brief than for a research paper.

Legal

Prioritizes verbatim statements, dates, names, and legally significant language. Flags hearsay and speculation.

Medical

Surfaces clinical findings, dosages, patient outcomes, and diagnostic reasoning. Filters small talk.

Research

Weights novel insights, data points, methodology, and citations. Deprioritizes repetition and filler.

P

Custom Prompt Engine

Tell the AI what you're building. It scans your content, understands the structure, and designs a precision extraction prompt tailored to your exact deliverable. No prompt engineering required.

From goal to prompt in seconds

You describe the output. The engine reverse-engineers the extraction logic. No trial and error, no wasted API calls.

Content-aware

The engine reads a sample of your transcripts before generating the prompt. It adapts to your specific content, not generic templates.

X

Duplicate Detection

When you process 50+ sources, the same idea shows up in different words across different files. Duplicate Detection finds blocks saying the same thing, clusters them, and lets you pick the best version. Runs locally. Free.

O

Obsidian Export

One click sends your curated content straight to your Obsidian vault. Wikilinks, frontmatter, tags, and folder structure included. Your extractions become a connected knowledge graph, not a pile of files.

[[wikilinks]]
YAML frontmatter
#auto-tags
folder mapping
T

Timecode Pointers

Toggle on source timestamps for every extracted block. Filmmakers and editors can jump straight to the exact moment in the original recording. Researchers can verify quotes against source material in seconds.

Filmmakers

Find the exact take. Click the timecode, hear the moment, mark it for your edit.

Editors

Verify every quote against the original audio. No more scrubbing through hours of footage.

Researchers

Cite with precision. Every extracted insight links back to the exact moment it was spoken.

System requirements

macOS 13 (Ventura) or later.

Dependencies: Python 3.10+, Homebrew, conda. All auto-installed on first launch.

Stay tuned.

Join the waitlist for early access.