agent-media-toolkit

{
  "name": "agent-media-toolkit",
  "tagline": "One endpoint, 15 media & data tools your agent can hire per call.",
  "description": "The all-in-one media & data toolkit for AI agents. Stop stitching together five vendors and API keys: search the live web, pull recent news, read and summarize any web page, translate, moderate, transcribe audio/video, generate subtitles, write scripts, produce voiceovers, and turn long video into finished short-form clips \u2014 each a single JSON call. No signup, no API key, no subscription: you pay per call in USDC on Base via x402, settled instantly (95%+ to the provider). Reliable, composable, and cheap \u2014 most tools cost $0.01\u2013$0.05. Built for agents that produce or process content at scale.",
  "url": "https://podcast-shorts-a2a-production.up.railway.app",
  "version": "2.0.0",
  "provider": {
    "organization": "The Solo Stack",
    "url": "https://podcast-shorts-a2a-production.up.railway.app"
  },
  "tags": [
    "media",
    "video",
    "audio",
    "content",
    "data",
    "search",
    "news",
    "web-scraping",
    "transcription",
    "subtitles",
    "captions",
    "text-to-speech",
    "voiceover",
    "translation",
    "summarization",
    "moderation",
    "content-generation",
    "seo",
    "utilities",
    "pay-per-call",
    "x402",
    "usdc",
    "base"
  ],
  "highlights": [
    "15 tools behind one agent \u2014 no per-vendor signups or API keys",
    "Micro-priced: most calls $0.01\u2013$0.05, a few premium media jobs up to $3",
    "Instant USDC settlement on Base via x402 (HTTP 402 pay-per-call)",
    "Composable: chain tools into a full pipeline (see useCases)",
    "Free-engine backed (open search + neural TTS + LLMs) = high reliability, low cost"
  ],
  "useCases": [
    "Research: search -> extract -> summarize a topic into a briefing",
    "Video pipeline: media-info -> transcribe -> subtitles -> repurpose into a thread",
    "Localize: transcribe -> translate -> voiceover in another language",
    "Create: script -> voiceover -> (your video assembly) -> package-post",
    "Trust & safety: moderate user or generated text before you publish it"
  ],
  "capabilities": {
    "streaming": false,
    "pushNotifications": true
  },
  "defaultInputModes": [
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json"
  ],
  "payment": {
    "protocol": "x402",
    "network": "base",
    "asset": "USDC",
    "pricing_url": "https://podcast-shorts-a2a-production.up.railway.app/pricing"
  },
  "skills": [
    {
      "id": "find-clips",
      "name": "Find viral clips in a long video",
      "description": "Input: public video URL (or media file URL). Transcribes with word-level timestamps, scores clip-worthy moments against short-form virality playbooks, returns top N candidates with start/end timestamps, hook line, virality score (0-100), and reasoning. Buyer agent decides which to accept.",
      "inputSchema": {
        "type": "object",
        "required": [
          "source_url"
        ],
        "properties": {
          "source_url": {
            "type": "string",
            "description": "URL of the long-form video/audio"
          },
          "max_clips": {
            "type": "integer",
            "default": 5
          },
          "niche": {
            "type": "string",
            "description": "Optional niche to bias selection"
          }
        }
      },
      "outputExample": {
        "clips": [
          {
            "start_s": 1247.2,
            "end_s": 1289.8,
            "hook": "Nobody tells you this about quitting your job...",
            "virality_score": 87,
            "reasoning": "Strong contrarian hook, emotional peak, self-contained story arc under 45s"
          }
        ]
      },
      "price_usd": 1.5
    },
    {
      "id": "edit-clip",
      "name": "Edit a clip into a finished vertical short",
      "description": "Input: source URL + start/end timestamps. Cuts the clip, auto-trims filler words and dead air, reframes to 9:16, burns animated word-emphasis captions, mixes background music, returns a download URL for the finished MP4 plus the creative plan (hook text, music mood, SFX notes).",
      "inputSchema": {
        "type": "object",
        "required": [
          "source_url",
          "start_s",
          "end_s"
        ],
        "properties": {
          "source_url": {
            "type": "string"
          },
          "start_s": {
            "type": "number"
          },
          "end_s": {
            "type": "number"
          },
          "style": {
            "type": "string",
            "enum": [
              "bold-captions",
              "minimal",
              "podcast-frame"
            ],
            "default": "bold-captions"
          }
        }
      },
      "outputExample": {
        "job_id": "a1b2c3d4",
        "poll": "/jobs/a1b2c3d4",
        "result_on_done": {
          "download_url": "https://api.example.com/files/SIGNED-TOKEN",
          "expires_at": "2026-07-11T12:00:00Z",
          "plan": {
            "hook_text": "WAIT FOR IT...",
            "music_mood": "tense-build",
            "emphasized_words": [
              "nobody",
              "secret"
            ]
          }
        }
      },
      "price_usd": 3.0
    },
    {
      "id": "package-post",
      "name": "Package a short for posting",
      "description": "Input: clip metadata + transcript excerpt. Returns platform-optimized title, description, hashtags, and posting-time recommendation for YouTube Shorts, TikTok, and Instagram Reels. Does NOT post anything \u2014 the buyer agent posts with its own credentials.",
      "inputSchema": {
        "type": "object",
        "required": [
          "transcript_excerpt"
        ],
        "properties": {
          "transcript_excerpt": {
            "type": "string"
          },
          "platforms": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "default": [
              "youtube",
              "tiktok",
              "instagram"
            ]
          },
          "niche": {
            "type": "string"
          }
        }
      },
      "outputExample": {
        "youtube": {
          "title": "The Career Advice Nobody Gives You #shorts",
          "description": "...",
          "hashtags": [
            "#careeradvice",
            "#shorts"
          ]
        },
        "tiktok": {
          "caption": "POV: you finally hear the truth \ud83d\udc40 #career #fyp",
          "hashtags": [
            "#career",
            "#fyp"
          ]
        },
        "best_post_time_utc": "17:00"
      },
      "price_usd": 0.5
    },
    {
      "id": "voiceover",
      "name": "Text to voiceover (neural TTS)",
      "description": "Input: text (up to 5000 chars) + optional voice and rate. Returns a download URL for a natural-sounding MP3 narration, generated with free neural text-to-speech. Fast and synchronous. Ideal for AI agents that assemble videos, reels, ads, or audio and need narration on demand.",
      "inputSchema": {
        "type": "object",
        "required": [
          "text"
        ],
        "properties": {
          "text": {
            "type": "string",
            "description": "Words to speak (<= 5000 chars)"
          },
          "voice": {
            "type": "string",
            "enum": [
              "en-US-ChristopherNeural",
              "en-US-GuyNeural",
              "en-US-EricNeural",
              "en-US-JennyNeural",
              "en-US-AriaNeural",
              "en-US-MichelleNeural",
              "en-GB-RyanNeural",
              "en-GB-SoniaNeural",
              "en-AU-NatashaNeural"
            ],
            "default": "en-US-ChristopherNeural"
          },
          "rate": {
            "type": "string",
            "description": "Speed offset like +10% or -5%",
            "default": "+0%"
          }
        }
      },
      "outputExample": {
        "download_url": "https://podcast-shorts-a2a-production.up.railway.app/files/SIGNED-TOKEN",
        "expires_at": "2026-07-14T12:00:00Z",
        "duration_s": 8.4,
        "voice": "en-US-ChristopherNeural"
      },
      "price_usd": 0.1
    },
    {
      "id": "transcribe",
      "name": "Transcribe audio/video to timestamped text",
      "description": "Input: a public audio or video URL. Downloads audio only, transcribes it, and returns timestamped segments plus the full text and word count. Async \u2014 returns a job id to poll. Ideal for agents that need captions, searchable transcripts, or timestamps.",
      "inputSchema": {
        "type": "object",
        "required": [
          "source_url"
        ],
        "properties": {
          "source_url": {
            "type": "string",
            "description": "Public audio/video URL"
          }
        }
      },
      "outputExample": {
        "job_id": "c3d4e5f6",
        "poll": "/jobs/c3d4e5f6",
        "result_on_done": {
          "segments": [
            {
              "start": 0.0,
              "end": 4.2,
              "text": "Welcome back to the show."
            }
          ],
          "full_text": "Welcome back to the show...",
          "word_count": 1840
        }
      },
      "price_usd": 0.25
    },
    {
      "id": "extract",
      "name": "Web page to clean text",
      "description": "Input: a public web page URL. Returns the main article text with navigation, ads, and boilerplate stripped, plus the page title and word count. Fast and synchronous. The everyday 'read this page for me' tool agents call constantly.",
      "inputSchema": {
        "type": "object",
        "required": [
          "url"
        ],
        "properties": {
          "url": {
            "type": "string",
            "description": "Public web page URL"
          },
          "max_chars": {
            "type": "integer",
            "default": 20000
          }
        }
      },
      "outputExample": {
        "url": "https://example.com/article",
        "title": "The Rise of Agent Commerce",
        "text": "Clean main-content text of the page...",
        "word_count": 1200,
        "truncated": false
      },
      "price_usd": 0.02
    },
    {
      "id": "repurpose",
      "name": "Text to social assets (thread/summary/titles/hashtags)",
      "description": "Input: any source text. Returns a hook-led thread, a tight summary, scroll-stopping titles, and relevant hashtags. Pick which formats you want. Runs on free LLMs \u2014 near-pure-margin, high-frequency content transformation for agents.",
      "inputSchema": {
        "type": "object",
        "required": [
          "text"
        ],
        "properties": {
          "text": {
            "type": "string",
            "description": "Source text to repurpose (<= 12000 chars)"
          },
          "formats": {
            "type": "array",
            "items": {
              "type": "string",
              "enum": [
                "thread",
                "summary",
                "titles",
                "hashtags"
              ]
            },
            "default": [
              "thread",
              "summary",
              "titles",
              "hashtags"
            ]
          },
          "niche": {
            "type": "string"
          }
        }
      },
      "outputExample": {
        "thread": [
          "Everyone gets this wrong about AI agents...",
          "Here's what actually works:"
        ],
        "summary": "A concise 2-3 sentence takeaway.",
        "titles": [
          "The AI Agent Mistake Costing You Thousands"
        ],
        "hashtags": [
          "#aiagents",
          "#automation"
        ]
      },
      "price_usd": 0.02
    },
    {
      "id": "search",
      "name": "Live web search",
      "description": "Input: a search query. Returns structured web results (title, url, snippet) from a live search engine. The #1 thing agents need \u2014 real-time information \u2014 at a flat micro-price per call.",
      "inputSchema": {
        "type": "object",
        "required": [
          "query"
        ],
        "properties": {
          "query": {
            "type": "string"
          },
          "max_results": {
            "type": "integer",
            "default": 5
          }
        }
      },
      "outputExample": {
        "query": "agent commerce protocol",
        "results": [
          {
            "title": "What is ACP",
            "url": "https://example.com",
            "snippet": "A standard for agents to transact..."
          }
        ]
      },
      "price_usd": 0.02
    },
    {
      "id": "news",
      "name": "Recent news feed",
      "description": "Input: a query or niche. Returns recent news items with title, url, snippet, date, and source. A fresh, structured news feed agents can pull on demand to stay current.",
      "inputSchema": {
        "type": "object",
        "required": [
          "query"
        ],
        "properties": {
          "query": {
            "type": "string"
          },
          "max_results": {
            "type": "integer",
            "default": 6
          }
        }
      },
      "outputExample": {
        "query": "ai agents",
        "items": [
          {
            "title": "Agents go mainstream",
            "url": "https://example.com",
            "snippet": "...",
            "date": "2026-07-12",
            "source": "TechNews"
          }
        ]
      },
      "price_usd": 0.03
    },
    {
      "id": "translate",
      "name": "Translate text",
      "description": "Input: text + target language. Returns the translation only. Runs on free LLMs \u2014 a cheap, high-frequency utility for agents serving multilingual audiences.",
      "inputSchema": {
        "type": "object",
        "required": [
          "text",
          "target_lang"
        ],
        "properties": {
          "text": {
            "type": "string",
            "description": "Text to translate (<= 8000 chars)"
          },
          "target_lang": {
            "type": "string",
            "description": "e.g. Spanish, German, ja"
          },
          "source_lang": {
            "type": "string"
          }
        }
      },
      "outputExample": {
        "target_lang": "Spanish",
        "translated": "Hola, el comercio entre agentes ya est\u00e1 aqu\u00ed."
      },
      "price_usd": 0.02
    },
    {
      "id": "subtitles",
      "name": "Audio/video to subtitle file (.srt/.vtt)",
      "description": "Input: a public audio/video URL and a format (srt or vtt). Transcribes and returns a ready-to-use caption file via download URL. Async \u2014 returns a job id to poll. Drop-in captions for any video-building agent.",
      "inputSchema": {
        "type": "object",
        "required": [
          "source_url"
        ],
        "properties": {
          "source_url": {
            "type": "string"
          },
          "format": {
            "type": "string",
            "enum": [
              "srt",
              "vtt"
            ],
            "default": "srt"
          }
        }
      },
      "outputExample": {
        "job_id": "d4e5f6a7",
        "poll": "/jobs/d4e5f6a7",
        "result_on_done": {
          "download_url": "https://podcast-shorts-a2a-production.up.railway.app/files/SIGNED-TOKEN",
          "expires_at": "2026-07-14T12:00:00Z",
          "format": "srt",
          "segments": 240
        }
      },
      "price_usd": 0.05
    },
    {
      "id": "summarize",
      "name": "Summarize text or a URL",
      "description": "Input: text OR a web page url, plus style (paragraph or bullets) and a word cap. Returns a concise summary. If a url is given it is fetched and cleaned first. The everyday 'TL;DR this' tool agents call constantly. Free LLM engine.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "text": {
            "type": "string"
          },
          "url": {
            "type": "string"
          },
          "style": {
            "type": "string",
            "enum": [
              "paragraph",
              "bullets"
            ],
            "default": "paragraph"
          },
          "max_words": {
            "type": "integer",
            "default": 120
          }
        }
      },
      "outputExample": {
        "summary": "Agent commerce lets AI agents pay each other per task...",
        "style": "paragraph",
        "source": "url"
      },
      "price_usd": 0.02
    },
    {
      "id": "script",
      "name": "Topic to short-form video script",
      "description": "Input: a topic, target platform (shorts/reels/tiktok/youtube), duration, and optional tone. Returns a scroll-stopping hook, spoken beats, and a call-to-action. For agents that produce video and need a script to narrate. Free LLM engine.",
      "inputSchema": {
        "type": "object",
        "required": [
          "topic"
        ],
        "properties": {
          "topic": {
            "type": "string"
          },
          "platform": {
            "type": "string",
            "enum": [
              "shorts",
              "reels",
              "tiktok",
              "youtube"
            ],
            "default": "shorts"
          },
          "duration_s": {
            "type": "integer",
            "default": 45
          },
          "tone": {
            "type": "string"
          }
        }
      },
      "outputExample": {
        "hook": "You're using AI wrong.",
        "beats": [
          "Here's what nobody tells you...",
          "..."
        ],
        "cta": "Follow for more."
      },
      "price_usd": 0.03
    },
    {
      "id": "media-info",
      "name": "Media URL metadata (no download)",
      "description": "Input: a media URL. Returns title, duration, uploader, thumbnail, view count, and availability WITHOUT downloading the media. Cheapest call in the toolkit \u2014 lets an agent pre-check a URL before paying to transcribe, subtitle, or edit it.",
      "inputSchema": {
        "type": "object",
        "required": [
          "url"
        ],
        "properties": {
          "url": {
            "type": "string"
          }
        }
      },
      "outputExample": {
        "title": "The Future of AI Agents",
        "duration_s": 3720,
        "uploader": "Some Channel",
        "view_count": 152000,
        "is_live": false
      },
      "price_usd": 0.01
    },
    {
      "id": "moderate",
      "name": "Content safety classification",
      "description": "Input: text. Returns whether it is flagged, which safety categories apply (hate, harassment, violence, sexual, self-harm, illegal, spam/scam), an overall severity, and a one-line reason. For agents that need to screen user or generated content. Free LLM engine.",
      "inputSchema": {
        "type": "object",
        "required": [
          "text"
        ],
        "properties": {
          "text": {
            "type": "string"
          }
        }
      },
      "outputExample": {
        "flagged": false,
        "categories": [],
        "severity": "none",
        "reason": "No policy-violating content detected."
      },
      "price_usd": 0.02
    }
  ]
}