> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://summarize.martino.im/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://summarize.martino.im/_mcp/server. # CLI Reference > **Note** > > All flags override the corresponding settings in `summarizer.yaml`. Use `--verbose` to see detailed status output during config loading, downloads, transcription, and summarization. ## Examples #### Basic ```bash # Uses default provider from YAML python -m summarizer --source "https://youtube.com/watch?v=VIDEO_ID" # Console entry point (after pipx or pip install) summarizer --source "URL" # Specific provider python -m summarizer --source "URL" --provider groq # Extract key insights python -m summarizer --source "URL" --provider gemini --prompt-type "Distill Wisdom" # Generate a Mermaid diagram python -m summarizer --source "URL" --provider openrouter --prompt-type "Mermaid Diagram" # Batch process python -m summarizer --source "URL1" "URL2" "URL3" # Local file python -m summarizer --type "Local File" --source "./lecture.mp4" # Text file (skip audio entirely) python -m summarizer --type "TXT" --source "./transcript.txt" # No config (all explicit) python -m summarizer \ --source "URL" \ --base-url "https://openrouter.ai/api/v1" \ --model "google/gemini-2.0-flash-exp:free" \ --api-key "sk-or-v1-YOUR_KEY" \ --prompt-type "Tutorial" \ --no-config ``` #### Fact-checking ```bash python -m summarizer \ --source "URL" \ --base-url "https://api.perplexity.ai" \ --model "sonar-pro" \ --prompt-type "Fact Checker" ``` #### Audio and Language ```bash # Speed up audio before Whisper (faster, may reduce accuracy) python -m summarizer --source "URL" --speed 2.0 # Aggressive speed-up (any positive value) python -m summarizer --source "URL" --speed 5.0 # Speed up video in visual mode (base64 path) python -m summarizer --source "URL" --provider nvidia --visual --speed 1.5 # Lock captions/transcription to Italian python -m summarizer --source "URL" --language "it" # Write the summary in Italian python -m summarizer --source "URL" --output-language "Italian" # Select passages before summarization python -m summarizer --source "URL" \ --use-jev-prefiltering \ --jev-include "a particular concept about this video to filter" \ --jev-exclude "Sponsorship and self-promotion" ``` ## Flag Reference | Flag | Description | Default | | ------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------- | | `--source` | Video URLs, file paths, or text files (multiple allowed) | Required | | `--provider` | Provider name from YAML | `default_provider` | | `--base-url` | API endpoint (overrides provider) | From YAML | | `--model` | Model identifier (overrides provider) | From YAML | | `--api-key` | API key (overrides `.env`) | - | | `--type` | `YouTube Video`, `Video URL`, `Local File`, `Google Drive Video Link`, `Dropbox Video Link`, `TXT` | `YouTube Video` | | `--prompt-type` | Summary style | From YAML defaults | | `--chunk-size` | Input text chunk size in characters (min 1000) | `120000` (from `summarizer.yaml`; code fallback `10000`) | | `--force-download` | Skip captions and download audio instead | `False` | | `--transcription` | `Cloud Whisper` (Groq Whisper API) or `Local Whisper` (local Whisper) | `Cloud Whisper` | | `--whisper-model` | `tiny`, `base`, `small`, `medium`, `large` | `tiny` | | `--speed` | Playback speed for audio preprocessing or visual-mode video. Reduces Groq cost (priced by duration) but may reduce accuracy. Values other than `1.0` skip YouTube captions. Any positive value. | `1.0` | | `--language` | `auto` or explicit code for captions/transcription | `auto` | | `--output-language` | Summary language; `auto`, `none`, or name | `auto` | | `--output-format` | `markdown`, `json`, or `html` | `markdown` | | `--parallel-calls` | Concurrent API requests | `10` (from `summarizer.yaml`; code fallback `30`) | | `--max-tokens` | Max output tokens per chunk | `4096` | | `--cobalt-url` | Cobalt base URL for fallback downloads | `http://localhost:9000` | | `--output-dir` | Output directory | `summaries` | | `--no-save` | Print to stdout only, no file output | `False` | | `--verbose`, `-v` | Detailed output | `False` | | `--visual` | Send video directly to a video-capable model | `False` | | `--use-jev-prefiltering` / `--no-use-jev-prefiltering` | Enable or disable transcript selection before summarization | From YAML (`false`) | | `--jev-provider` | Existing OpenRouter or TypeSafe provider used for scoring | `openrouter` | | `--jev-include` | Include only passages about this concept; blank means general relevance | `""` | | `--jev-exclude` | Exclude matching passages; exclusions take priority | `""` | | `--use-proxy` | Route supported requests through the configured HTTP proxy | From YAML | | `--config` | Path to config file | auto-detect | | `--no-config` | Ignore config file, use CLI args only | - | | `--init-config` | Generate example `summarizer.yaml` and exit | - | ## HTTP API Server Start a local FastAPI server that exposes the same functionality over HTTP: ```bash python -m summarizer serve ``` Customize host and port: ```bash python -m summarizer serve --host 0.0.0.0 --port 8080 ``` Interactive docs are available at `http://localhost:8000/docs`. See the [HTTP API guide](api-reference/http-api) for endpoint reference and example requests. > **Tip:** Use `--verbose` to see detailed status output during config loading, downloads, transcription with Whisper, and summarization. > > **Tip:** On Windows, do NOT use `--no-save` — Unicode output crashes stdout. Always let the tool save to file, then read it. > > **Tip:** `--chunk-size` has a hard minimum of 1000 characters. Values below 1000 are clamped automatically. ## Output Formats ### Markdown (default) Clean Markdown with optional bold titles. Saved as `.md`. ### JSON ```bash python -m summarizer --source "URL" --output-format json ``` Includes metadata: ```json { "source": "https://youtube.com/watch?v=VIDEO_ID", "generated_at": "2026-06-01T20:00:00", "prompt_type": "Distill Wisdom", "model": "gemini-3.5-flash-lite", "summary": "..." } ``` ### HTML ```bash python -m summarizer --source "URL" --output-format html ```