Pick a target — any audio, video, or document file to convert to text and combine with prompts to generate text, audio, image, music, and video assets.
Start with common audio, video, document, or image files.
Turn the original source into text you can use.
Create useful written content and optional spoken narration from the text.
Use the same text to create images, videos, or music.
Your target is processed into text through transcription or document extraction. The text is then combined with prompts to generate text, audio, image, music, and video outputs.
Upload MP3/MP4 files from your computer, import from Google Drive, paste podcast feed or episode URLs, use direct public MP3/MP4 URLs, or paste approved streaming URLs from YouTube, Vimeo, Twitch, Dailymotion, TikTok, Instagram, Facebook, X/Twitter, or SoundCloud.
Upload PDF, EPUB, PPTX, DOCX, XLSX, TXT, PNG, JPEG, or TIFF files, import from Google Drive, or scrape URL/HTML pages. Extract with 7 services: Local EPUB Text, Mistral OCR, GLM-OCR, OpenAI, Google Gemini, Grok, or Kimi.
Go beyond transcription. Generate narrated audio, cover images, original music, and video clips from your content using the latest generative AI models.
Convert summaries to narrated audio using 6 text-to-speech services: OpenAI TTS, ElevenLabs TTS, Deepgram Aura TTS, Gemini TTS, Grok TTS, or Groq Orpheus TTS. Choose from multiple voices and output formats.
Create cover art, thumbnails, and promotional images with 3 image services: ChatGPT Image, Gemini Image, or Grok Image. Generate 1-3 images per job with customizable dimensions and aspect ratios.
Generate original theme music with AI-written lyrics. Choose from 7 genres: Pop, Rock, Rap, Country, Folk, Jazz, Electronic. Powered by Eleven Music, MiniMax Music, or Gemini Music.
Create explainer clips, highlights, intros, outros, and social media videos with 2 video services: Gemini Veo or Grok Video. All prompts include safety filtering.
Content flows through a configurable pipeline. Each step can be customized with different providers and models. Optional steps are skipped if not enabled.
Uploaded files, Google Drive imports, direct URLs, and approved streaming links are fetched and normalized before text extraction.
Every source becomes reusable text through the matching extraction path.
Dynamic prompts are assembled, the LLM generates structured outputs, and narration can be synthesized in the same stage.
Optional downstream media turns the generated text into visual and audio assets.
Built for reliability and scale with enterprise-grade infrastructure.
12 services: Groq Whisper, DeepInfra Whisper, Gladia, AssemblyAI, Deepgram Nova 3, Grok STT, Soniox, Mistral Voxtral Mini, YouTube Captions, ScrapeCreators, deAPI, or Supadata.
5 providers: OpenAI, Claude, Google Gemini, Grok, and Groq.
6 services: OpenAI TTS, ElevenLabs TTS, Deepgram Aura TTS, Gemini TTS, Grok TTS, or Groq Orpheus TTS.
3 services: ChatGPT Image, Gemini Image, or Grok Image. Supports square, landscape, portrait, and provider-specific aspect ratios.
Eleven Music (music_v1), MiniMax Music (music-2.6), Gemini Music (lyria-3-pro-preview). 7 genres available: Pop, Rock, Rap, Country, Folk, Jazz, and Electronic.
2 services: Gemini Veo or Grok Video. Durations, resolutions, and aspect ratios vary by provider.
Generated files are saved under the configured artifact output root. When S3-compatible storage is configured, uploads and generated media can also use bucket-backed URLs.
7 services: Local EPUB Text, Mistral OCR, GLM-OCR, OpenAI, Google Gemini, Grok, or Kimi. Supports PDF, EPUB, DOCX, PPTX, XLSX, PNG, JPEG, TIFF, and TXT uploads, plus URL/HTML page scraping.
AutoShow accepts podcast feed and episode URLs; approved streaming URLs for YouTube, Vimeo, Twitch, Dailymotion, TikTok, Instagram, Facebook, X/Twitter, and SoundCloud; direct public MP3/MP4 media URLs; URL/HTML pages; uploaded audio and video files from your computer; uploaded document and image files; and Google Drive imports when configured. Supported uploads include audio files (MP3, WAV, M4A, FLAC, OGG, AAC, WMA, MPEG/MPGA), video files (MP4, MOV, AVI, MKV, WEBM, WMV, FLV, M4V), documents (PDF, EPUB, DOCX, PPTX, XLSX, TXT), and images (PNG, JPG/JPEG, TIFF/TIF).
For speaker identification, use Gladia, AssemblyAI, Deepgram Nova 3, Grok STT, Mistral Voxtral Mini, or Soniox. For fast local or direct media without speaker labels, use Groq Whisper or DeepInfra Whisper. For streaming URLs, use YouTube Captions when available, or ScrapeCreators, Gladia, deAPI, or Supadata.
Uploads and remote sources are subject to configured size limits: uploads default to 1 GB, and remote documents default to 300 MB. Long audio is segmented when needed, with 10-minute chunks for non-diarized local/direct Whisper transcription and 30-minute fallback chunks for other long audio.
5 LLM providers are configured: OpenAI, Claude, Google Gemini, Grok, and Groq. Structured JSON output uses retry and fallback logic when a selected provider fails.
First, an LLM generates a detailed scene description based on your content. Then, the scene is rendered using Gemini Veo or Grok Video. Video types include explainer, highlight, intro, outro, and social clips.
Generated files are saved under the configured artifact output root. If S3 storage is configured with Railway Storage Buckets or another S3-compatible service, uploads and generated media can also be stored in the bucket with URL-backed access.
AutoShow supports 7 genres: Pop, Rock, Rap, Country, Folk, Jazz, and Electronic. An LLM first writes original, copyright-safe lyrics tailored to your content, then the music is composed.
Transform your content with AI transcription, summarization, and generation.
Usage based pricing - No subscriptions or hidden fees