Turn Claude into a creative engine

Choose your agent, connect your account, and create images, video clips, and voice from chat. Start with a free connection and upload check.

1

Copy the connector URL

One URL. No API key, no local process, nothing to install.
https://api.agent-media.ai/mcp
2

Add it in Claude

Open Customize → Connectors, select + → Add custom connector, paste the URL, and connect your agent-media account. Enable agent-media in your conversation’s connector menu. The same remote connection works in Claude.ai, Desktop, and Cowork.
3

Check your connection for free

After signing in, start a new conversation with agent-media enabled. Ask your agent:
Use agent-media to list available models and open its image upload panel. Do not generate anything yet.
Opening the panel confirms authenticated upload access. Generation needs credits; ask for a quote before your first creation.

Adding the connector and signing in are separate steps. If your agent cannot see agent-media, check that it is enabled in this conversation. If the new upload tools are missing, ask it to call upload_image with an empty object to open the existing panel. Images expire after 24 hours.

Available skills

Each runs from the CLI, the skill pack, or the REST API with one Bearer token. Over MCP, agents use the nine loose tools instead: see the docs.

Make Subtitles

Burn TikTok / Hormozi-style captions onto any vNext video (R2-hosted). Auto-transcribes via Whisper when transcript is omitted. Styles: hormozi (default), tiktok, minimal.

15 credits · ~20sRun →

Make Podcast

Two saved characters recording a podcast in ONE room , the camera cuts to whoever is speaking, and each actor stays in their IDENTICAL seat, desk and mic position across every cut. Provide character_a and character_b (saved char_… ids from list_characters, or https image URLs) and an ordered `script` of A/B dialogue turns (each { speaker: "A" | "B", line: "…" }). The pipeline renders ONE shared two-shot, locks a close-up per actor, animates every turn with native lip-synced Seedance voice (each actor keeps a consistent look AND voice across the whole episode), and hard-cuts the turns together as a 9:16 vertical video, with the silence before and after each turn cut. Each turn renders as the shortest 5/10/15s take its words fill (~2.9 words/sec: up to 15 words = 5s, 16-31 = 10s, 32-46 = 15s); longer turns split. Write plain everyday words: no rare or made-up words, no stage directions, emoji or links. Captions are OPT-IN , ask the user first, then set subtitles:true.

~280 to 1400 credits · 8 to 30 minRun →

Agent-Media UGC Video

The ONE tool for UGC video. Give a `script` (any length) and optionally a `person` description, an `image` (photo), or a `character` (saved char_… or sheet URL); it returns the finished vertical video. Short script → one clip; long monologue → full multi-take (never trimmed); pass `broll_url` → narrated b-roll overlay. Captions are OPT-IN , ASK the user if they want them (and which style) before generating; set `captions:true` only if they say yes. You never pick a sub-tool.

from ~155 credits · 6 to 25 minRun →

Prefer raw HTTP?

Every skill is also a REST endpoint, with the same Bearer token. Poll GET /v1/skills/runs/<id> for the result.

curl -X POST \
 https://api.agent-media.ai/v1/skills/make_ugc/run \
 -H "Authorization: Bearer $TOKEN" \
 -H "Content-Type: application/json" \
 -d '{ "script": "...", "person": "a friendly woman" }'