AutoShow
github.com
- Web
- API
- Self-hosted
What AutoShow is
AutoShow is a free, open-source application for processing audio and video with AI services. It can extract audio from YouTube videos, streaming platforms, and direct file uploads, then produce transcriptions, summaries, chapters, speech, images, and music. Listed transcription choices include Groq Whisper, DeepInfra, YouTube Captions, and HappyScribe, with automatic speaker diarization. OpenAI GPT, Claude, and Google Gemini can create episode descriptions, summaries, and chapters. Text-to-speech is available through OpenAI or ElevenLabs voices, while cover images and background music can also be generated. AutoShow provides web, API, and self-hosted options, with Docker deployment and a local web interface using localhost:4321 by default. Its API documentation covers health checks, jobs, models, processing, uploads, and media processing. Production documentation describes source URL validation, cost estimation, structured JSON logs, and optional HTTP log forwarding. Google Drive OAuth setup remains manual.
Who it suits
AutoShow suits teams and developers handling audio or video who want a free, self-hosted or API-based workflow with configurable AI providers.
Good to know, and what to watch
- Free and open-source
- Extracts audio from videos and uploads
- Automatic speaker diarization
- Generates summaries and chapters
- Supports Docker deployment
- Google Drive OAuth setup is manual
- Requires provider configuration for AI services
The verdict
AutoShow combines media ingestion, transcription, summarization, and generated media in one open-source project. Its self-hosted, API, and web options fit teams that can manage configuration and provider accounts.
What the maker publishes
- API
- The README links documentation for API endpoints covering health checks, jobs, models, processing, file uploads, and media processing. source
- API
- The project documents an HTTP API with its local base URL at http://localhost:4321/api and says to use the deployment domain in production. source
- Configuration
- The CLI documentation describes optional Resend email and Google Drive configuration checks; Google Drive OAuth client setup remains manual. source
- Configuration
- The configuration guide documents optional Resend email and Google Drive setup checks. source
- Costs
- The README links to documentation covering provider cost estimates and runtime totals. source
- Deployment
- The project supports Docker deployment and can serve a web interface locally; the README gives localhost:4321 as the default URL. source
- Deployment
- The README documents Docker deployment and a web interface available at the local URL printed by the CLI, defaulting to localhost:4321. source
- Docker requirements
- The Docker guide says the repository-root .env file must include required email, provider-key, and S3 settings for the documented Compose commands. source
- Generated media
- The README describes text-to-speech with OpenAI or ElevenLabs voices, AI-generated cover images, and background music generation with ElevenLabs. source
- Generated media
- The README describes converting summaries to speech with OpenAI or ElevenLabs voices, creating cover images from AI prompts, and generating background music with ElevenLabs. source
- Google Drive setup
- The guide says Google Drive OAuth client setup remains manual because the web client flow is not reliably covered by gcloud. source
- Inputs
- It can extract audio from YouTube videos, streaming platforms, and direct file uploads. source
- Inputs
- It can extract audio from YouTube videos, streaming platforms, and direct file uploads. source
- Integrations
- The model configuration documentation lists integrations including OpenAI, Anthropic, Google Gemini, Groq, ElevenLabs, AssemblyAI, Deepgram, HappyScribe, Mistral, Runway, and YouTube Captions. source
- License
- The package metadata identifies the project author as Anthony Campolo and its license as MIT. source
- Logging
- The README lists structured production JSON logs with request IDs and severity levels, plus optional HTTP log drain forwarding. source
- Maker
- The repository is hosted under the GitHub organization autoshow; the pages reviewed do not state the maker's headquarters or founding year. source
- Proxy configuration
- The configuration guide documents an option to trust forwarded proxy IP headers and a shared token required before those headers are trusted. source
- Purpose
- AutoShow is a full-stack application for processing audio and video with AI transcription, summarization, text-to-speech, image generation, and music generation. source
- Purpose
- AutoShow is a full-stack application for processing video and audio with AI transcription, summarization, text-to-speech, image generation, and music generation. source
- Security
- The model configuration documentation says production model execution uses source URL validation against a public-network SSRF guard and USD cost estimation before job creation. source
- Summarization
- OpenAI GPT, Claude, and Google Gemini models can generate episode descriptions, summaries, and chapters. source
- Summarization
- OpenAI GPT, Claude, and Google Gemini models can generate episode descriptions, summaries, and chapters. source
- Transcription
- The README lists Groq Whisper, DeepInfra, YouTube Captions, and HappyScribe transcription, with automatic speaker diarization. source
Checked against the maker's pages on 8 Oct 2026.