Skip to content
SPECIFICTION
Get listed

AutoShow

github.com

WebAPISelf-hosted
Visit github.com
Spec score 7.4 #16 of 22 in Podcast Show Notes Software

What it is

AutoShow is a free, MIT-licensed full-stack application for AI processing of audio and video. It accepts direct uploads and can extract audio from YouTube videos and streaming platforms. Transcription options include Groq Whisper, DeepInfra, YouTube Captions, and HappyScribe, with automatic speaker diarization. OpenAI GPT, Claude, and Google Gemini can produce episode descriptions, summaries, and chapters. The project also documents text-to-speech with OpenAI or ElevenLabs voices, generated cover images, and background music through ElevenLabs. It is available as a web interface, API, or self-hosted deployment, with Docker support and localhost:4321 as the documented local address. API endpoints cover health checks, jobs, models, processing, uploads, and media processing. Production documentation describes source-URL SSRF validation, USD cost estimates before jobs, structured JSON logs, and optional HTTP log forwarding. Google Drive OAuth setup remains manual.

Spec sheet

Purpose
AutoShow is a full-stack application for processing video and audio with AI transcription, summarization, text-to-speech, image generation, and music generation.Read 8 Oct 2026 · github.com
Deployment
The README documents Docker deployment and a web interface available at the local URL printed by the CLI, defaulting to localhost:4321.Read 8 Oct 2026 · github.com
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.Read 8 Oct 2026 · github.com
Integrations
The model configuration documentation lists integrations including OpenAI, Anthropic, Google Gemini, Groq, ElevenLabs, AssemblyAI, Deepgram, HappyScribe, Mistral, Runway, and YouTube Captions.Read 4 Oct 2026 · github.com
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.Read 4 Oct 2026 · github.com
License
The package metadata identifies the project author as Anthony Campolo and its license as MIT.Read 4 Oct 2026 · github.com
Maker
The repository is hosted under the GitHub organization autoshow; the pages reviewed do not state the maker's headquarters or founding year.Read 8 Oct 2026 · github.com
Configuration
The configuration guide documents optional Resend email and Google Drive setup checks.Read 8 Oct 2026 · github.com
Costs
The README links to documentation covering provider cost estimates and runtime totals.Read 8 Oct 2026 · github.com
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.Read 8 Oct 2026 · github.com
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.Read 8 Oct 2026 · github.com
Google Drive setup
The guide says Google Drive OAuth client setup remains manual because the web client flow is not reliably covered by gcloud.Read 8 Oct 2026 · github.com
Inputs
It can extract audio from YouTube videos, streaming platforms, and direct file uploads.Read 8 Oct 2026 · github.com
Logging
The README lists structured production JSON logs with request IDs and severity levels, plus optional HTTP log drain forwarding.Read 4 Oct 2026 · github.com
Proxy configuration
The configuration guide documents an option to trust forwarded proxy IP headers and a shared token required before those headers are trusted.Read 8 Oct 2026 · github.com
Summarization
OpenAI GPT, Claude, and Google Gemini models can generate episode descriptions, summaries, and chapters.Read 8 Oct 2026 · github.com
Transcription
Listed transcription options include Groq Whisper, DeepInfra, YouTube Captions, and HappyScribe, with automatic speaker diarization.Read 8 Oct 2026 · github.com

Strong points and limits

Strong points

  • Open-source MIT license
  • Transcription with speaker diarization
  • Generates summaries and chapters
  • Web, API, and self-hosted options
  • Production SSRF and cost checks

Limits

  • Google Drive OAuth setup is manual
  • Requires provider keys and S3 settings
  • Generated services depend on external providers

Who it suits

It suits developers or teams wanting a self-hosted or API-based media-processing application. Docker deployment and documented provider integrations support configurable installations.

Verdict

AutoShow brings transcription, summarization, speech, images, and music generation into one deployable project. Its documentation is oriented toward operators who can configure providers, Docker, storage, and optional integrations.

Where Specifiction places it

Alternatives to AutoShowAll alternatives →