varg.ai

Generate music from a text description — a song with vocals, or an instrumental track. Returns an audio file URL. Describe genre, mood, instruments and tempo; for a song, include the lyrics or what they should be about. Set instrumental=true for background music with no vocals. Tracks take 30-90 seconds. By default this blocks until the audio is ready; if the wait runs out you get a job_id to poll with get_job. For other music models (lyria_3_5, mureka_9_5, …) or provider-specific options, use list_models({ tool: "music" }), get_tool("music", model), and call_tool({ tool: "music", … }).

Generate speech (text-to-speech) from text. Returns an audio file URL. Pick a voice with search_voices first, or pass a voice name directly (e.g. "Sarah", "Brian"). The default voice is Rachel if none is specified. The text can be in any language — the voice will speak it naturally.

Generate a video from a text description, an image, or another video. Three modes: - Text-to-video: just a prompt (default) - Image-to-video: pass from_image to animate a still image - Video-to-video: pass from_video to transform or edit existing footage Videos take 1-5 minutes. By default this returns a job_id immediately — poll with get_job(job_id) or re-run with wait=true to block. For other video models (kling, ltx, grok-imagine, …) or provider-specific options, use list_models({ tool: "video" }), get_tool("video", model), and call_tool({ tool: "video", … }).

Rank spend by one or two dimensions — which models, kinds of work, folders, API keys, people, creators or sources cost the most. Rows plus `other` always add up to `total`. With compare=previous_period each row also carries its previous spend and change_pct — the way to explain an increase. Amounts are credits, in the `_credits` fields: spend_credits 1234 is 1,234 credits. Report amounts in credits, never as money. Spend is usage charges counted when they were posted to the ledger, in [from, to). Group keys "none" (no value) and "hidden" (another team member's attribution, when meta.attributio…

Media files generated per hour, day, week or month in the given timezone, split into video, image, audio and other, plus the range total. Every generated file counts once, when it was made: clips made inside a render and files deleted since count; uploads and cache replays (an existing file served again) do not. Filters apply through the job that made the file. Counted by creation time (meta.time_basis created_at), not by when spend was posted. Buckets with is_partial=true are cut by the range or still in progress.

How much the account spent in a period and what is left: spend, charges, jobs, runs (a run is a request plus everything it spawned, e.g. a render and its clips), spend on jobs that failed or were cancelled, the same numbers for the comparison period, and the current balance with subscription/rollover expiry. Amounts are credits, in the `_credits` fields: spend_credits 1234 is 1,234 credits. Report amounts in credits, never as money. Spend is usage charges counted when they were posted to the ledger, in [from, to). Use get_analytics_breakdown to see what drove the spend. Shows a spend card.

Spend per hour, day, week or month in the given timezone, optionally split by one dimension (top groups + `other`). Amounts are credits, in the `_credits` fields: spend_credits 1234 is 1,234 credits. Report amounts in credits, never as money. Spend is usage charges counted when they were posted to the ledger, in [from, to). Buckets with is_partial=true are cut by the range or still in progress.

Show which team and folder this connection is working in, and whether that is still valid. Call this when a tool reports it cannot reach the connection's team.

Get one file's URL, media type, size, and creation date.

Check a job and collect its result. Use when a previous call returned a job_id that had not finished. A multi-step pipeline job can pause with status 'awaiting_confirmation' — review its step output with the user, then call confirm_job.

Explain what a job and its whole run were charged, from the ledger: every job in the run (a render and each clip, image and voice-over it generated) with its charges, including partial charges on failed or cancelled steps. Estimates and credits still held for unfinished work are reported beside the charges, never inside them. Accepts any job id in the run. Amounts are credits (the `_credits` fields) — report them as credits, never as money.

Recover how a file was made — the job, tool, model, and exact input that produced it. Use this to reproduce or tweak an earlier result. API docs: https://docs.varg.ai/api-reference/lineage/resolve-a-file-to-the-job-that-created-it

Get one preset by id, including its `tools` field — the ready-to-merge fragment for each tool this preset can be delivered into. Use the id returned by search_presets. The `tools` fragment contains the actual provider value (e.g. a higgsfield style UUID) placed at the correct request path; merge it into your call_tool body to apply the preset.

Get a template's full details, including its TSX source. To customise a template, read the source here, edit it, and pass it to render_video — v2 templates render as-is and have no variable substitution.

Get the input schema for a capability, and optionally the models that implement it. Call with just `tool` for the generic schema. Add `model` to get that model's exact schema, including provider-specific options that the generic schema does not list. Use `list_models: true` to page through the model catalog for this capability. The same schema, as a readable Markdown spec with inputs, limits and routes: https://varg.ai/models/<model>.md (index: https://varg.ai/models/llms.txt). Prices come only from the `*_credits` fields here or estimate_cost, never from the spec page — quote them in credit…

The charges behind the numbers: with the same range and filters, these rows add up exactly to the breakdown row or chart bar they came from. group=run groups them by run and adds run_total_charged_credits — everything the run was ever charged — next to spend_in_range_credits, the part that matched. sort=amount finds the most expensive. Amounts are credits, in the `_credits` fields: spend_credits 1234 is 1,234 credits. Report amounts in credits, never as money. Spend is usage charges counted when they were posted to the ledger, in [from, to). Page with next_cursor. Explain one run with get_job_…

List your files on varg.ai. Their URLs are usable as inputs to call_tool. Scoped to whichever account this connection works in — see get_current_team.

List your recent jobs (newest first, up to 50) with status, model, prompt, result URL and cost in credits. Call get_job for one job's full result. Shows the user a recent-jobs list.

List available models across all capabilities, with routes and per-model price estimates in credits (pricing.min_user_price_credits = the cheapest case, user_price_estimate_credits = the worst case). Filter by tool to narrow it down. Shows the user model cards.

List the teams you can work in, and show which one this connection currently uses. Each connection (Claude Desktop, Cursor, VS Code — each is a separate registration) has its own team. That is the point: one of your agents can work in Marketing while another works in Product. Generations are billed to whichever team the connection is set to, and files land in that team's library.

List varg's generation capabilities (video, image, speech, music, transcription, ffmpeg, render, …). Start here, then call get_tool to see the input schema for the one you want.

List your folders. Pass a folder id to call_tool or upload_file to keep a session's output together. Folders belong to one account, so this lists the ones in whichever team this connection works in — a personal folder is not visible from a team connection, and vice versa (see get_current_team).

Poll a job's status. App-only tool used by views to track progress.

Render a multi-scene video from TSX using varg's React-like components. Returns job_id immediately by default; set wait=true to block. Available components: Render, Clip, Video, Image, Speech, Music, Captions, Overlay, TalkingHead, Title, Subtitle, Split, Grid, Slider, Swipe, Packshot. Example TSX: ```tsx import { Render, Clip, Video, Speech, Captions, Overlay } from "vargai/react"; export default ( <Render width={1080} height={1920}> <Clip duration={5}> <Video prompt="sunset over the ocean, cinematic" model="kling-v3" /> <Overlay> <Speech text="Watch the sun set." …

Find presets — voices for text-to-speech, styles, and other reusable settings. This replaces the old voice catalog. Each result includes a `tools` field: the ready-to-merge fragment for each tool this preset can be delivered into (e.g. `tools.image` for a style, `tools.speech` for a voice). Merge that fragment into your call_tool request body to apply the preset — the actual provider value (a higgsfield style UUID, an elevenlabs voice_id, …) is already placed at the correct path inside it. Do NOT pass the preset `id` itself to the provider; it is a varg surrogate the provider will reject. An…

Find a voice for text-to-speech. Search by name, description, or describe what you want in words for ranked recommendations. Returns voices with names, descriptions, and metadata (gender, accent, language). Use the voice name or id with generate_speech. Shows the user playable voice cards. Examples: - search_voices({ query: "Sarah" }) — find by name - search_voices({ intent: "warm female narrator for a documentary" }) — get recommendations - search_voices({ filters: { gender: "male", accent: "british" } }) — filter by metadata

Point this connection at a team, or back at your personal account. This is persistent and affects only THIS connection — the other editors and desktop apps you have connected keep their own teams. It takes effect immediately, including for anything already running. You must already be a member of the team; this chooses among teams you have, it does not grant access to new ones.

Upload a file to varg.ai and get a hosted URL, usable in call_tool's `files: [{url}]`. Three ways to provide the file (provide exactly one): 1. path — local file path. ONLY works when this MCP server runs on the same machine as the file (local stdio, e.g. Claude Code with a local server). On the hosted server (mcp.varg.ai) local paths are unreadable — if the file is on the USER's device, call upload_file_widget instead. 2. url — pass a URL and the server fetches it (works everywhere) 3. data — base64-encoded content. Small files only (max 2MB decoded) — base64 through tool argumen…

Open an inline file picker so the user can upload a file from their device. THE way to get a user's local file in chat UIs (Claude.ai, ChatGPT). Call this FIRST whenever the user references a file on their device and you have no URL for it: "my photo", "this video", "I have a file", "use my image", "у меня есть файл", or they want to edit/animate/transcribe something of their own. Do NOT ask them to paste a URL and do NOT try upload_file with a local path (unreadable on the hosted server). The user picks a file in the widget; it uploads and registers automatically (no complete_upload needed)…

Render a published template to video as-is. For a customised version, use get_template, edit the TSX, and call render_video.