# Argil - [Argil MCP server](https://docs.argil.ai/v2/mcp/overview.md): Generate images, videos and audio with Argil from ChatGPT, Claude, Grok, Gemini, Claude Code or your own agent. - [Connect](https://docs.argil.ai/v2/mcp/connect.md): Add Argil to ChatGPT, Claude, Grok, Gemini, Claude Code, Codex, Gemini CLI or the Grok CLI. - [Build an agent](https://docs.argil.ai/v2/mcp/agents.md): Give an agent built on the Anthropic, OpenAI or xAI APIs, or on an agent framework, access to Argil. - [How it works](https://docs.argil.ai/v2/mcp/how-it-works.md): Generations that take minutes, using your files, and what you pay. - [Tools](https://docs.argil.ai/v2/mcp/tools.md): Every tool of the Argil MCP server, its arguments and what it returns. - [Troubleshooting](https://docs.argil.ai/v2/mcp/troubleshooting.md): Common problems, error codes, security and technical details. - [Models](https://docs.argil.ai/v2/models/overview.md): Every model you can generate with, its modes and its price. - [Seedance 2.5](https://docs.argil.ai/v2/models/seedance-2-5.md): Generate a video with Seedance 2.5 from text, from a first and/or last frame, or guided by references (up to 30 images, 10 videos, 10 audios); or extend or edit an input video. Up to 30 s, 480p/720p/1080p. - [MiniMax H3 Max](https://docs.argil.ai/v2/models/minimax-h3-max.md): Generate a 5–15 s video with fal’s MiniMax H3 Max from text, from a start (and end) frame, or guided by up to 12 image, video and audio references. 480P/768P, 1080P in reference mode. - [FLUX 3 Max](https://docs.argil.ai/v2/models/flux-3-max.md): Generate a 5–20 s video with fal’s FLUX 3 Max from text, or from a start (and optional end) frame. 720p or 1080p, native audio. - [LTX 2.3](https://docs.argil.ai/v2/models/ltx-2-3.md): Generate a video with Lightricks LTX 2.3 from text, from an image, or synced to an audio track (2–20 s). Up to 20 s, 1080p, with audio. - [Kling 2.6 Pro Motion Control](https://docs.argil.ai/v2/models/kling-2-6-pro-motion-control.md): Transfer the motion of a reference video onto a character image with Kling 2.6 Pro. Billed per second of the motion video. - [Seedance 2.0](https://docs.argil.ai/v2/models/seedance-2-0.md): Generate a video with Seedance 2.0 from text, from a first and/or last frame, or guided by references (up to 9 images, 3 videos, 3 audios). Up to 15 s. - [Seedance 2.0 Mini](https://docs.argil.ai/v2/models/seedance-2-0-mini.md): Generate a video with Seedance 2.0 Mini from text, from a first and/or last frame, or guided by references (up to 9 images, 3 videos, 3 audios). Up to 15 s. - [Pi Video](https://docs.argil.ai/v2/models/pi-video.md): Generate a video with PrunaAI Pi Video from text, from an image, or from an image synced to an audio track. Up to 10 s (audio: its length), 720p or 1080p, draft mode for cheap previews. - [Grok Imagine Video 1.5](https://docs.argil.ai/v2/models/grok-imagine-video-1-5.md): Generate a video with xAI Grok Imagine Video 1.5 from text, from a start (and end) image, or guided by up to 7 reference images. 480p/720p, up to 15 s (10 s with references). - [MiniMax H3](https://docs.argil.ai/v2/models/minimax-h3.md): Generate a 5–15 s video with MiniMax H3 from text, from a start (and end) frame, or guided by reference images, videos and audios. 480P (H3 Max, fastest), 768P or 2K. - [Argil Atom](https://docs.argil.ai/v2/models/argil-atom.md): A talking-head video of an avatar image: from a script a voice speaks (`script-to-video`, the voice's TTS model, billed as its characters, free on your own key, plus the lip-sync seconds) or from a speech audio (`audio-to-video`, billed per second of audio). - [Nano Banana 2.1](https://docs.argil.ai/v2/models/nano-banana-2-1.md): Generate or edit an image with Nano Banana 2.1. - [Grok Imagine Image 2.0](https://docs.argil.ai/v2/models/grok-imagine-image-2-0.md): Generate, edit or compose images (up to 5 references) with xAI Grok Imagine Image 2.0. - [GPT Image 2.5 Flare](https://docs.argil.ai/v2/models/gpt-image-2-5-flare.md): Generate, or edit and restyle up to 16 images, with OpenAI GPT Image 2.5 Flare (faster everyday generation). Minimum and 1K–4K output. - [GPT Image 2.5 Sunburst](https://docs.argil.ai/v2/models/gpt-image-2-5-sunburst.md): Generate, or edit and restyle up to 16 images, with OpenAI GPT Image 2.5 Sunburst (fine detail and precise editing, slower). Minimum and 1K–4K output. - [GPT Image 2.6 Flare](https://docs.argil.ai/v2/models/gpt-image-2-6-flare.md): Generate, or edit and restyle up to 16 images, with OpenAI GPT Image 2.6 Flare (faster everyday generation). Complexity sets planning; quality sets render detail. Minimum and 1K–4K output. - [GPT Image 2.6 Sunburst](https://docs.argil.ai/v2/models/gpt-image-2-6-sunburst.md): Generate, or edit and restyle up to 16 images, with OpenAI GPT Image 2.6 Sunburst (fine detail and precise editing, slower). Complexity sets planning; quality sets render detail. Minimum and 1K–4K output. - [Seedream 5.0 Pro](https://docs.argil.ai/v2/models/seedream-5-0-pro.md): Generate an image from text, or edit and combine up to 10 reference images, with ByteDance Seedream 5.0 Pro. - [Ideogram 3.0 Character](https://docs.argil.ai/v2/models/ideogram-3-0-character.md): Generate consistent characters from a single reference photo using Ideogram. Maintains facial features across different scenes and poses. - [FLUX.1 Schnell](https://docs.argil.ai/v2/models/flux-1-schnell.md): Fast, cheap text-to-image with FLUX.1 Schnell (12B), or Redux variations of one image. FLUX.2 Klein 4B is better for quality and text. - [FLUX.2 Klein 4B](https://docs.argil.ai/v2/models/flux-2-klein-4b.md): Blazing fast FLUX.2 [klein] 4B: text to image, or a prompt-driven edit of up to 4 reference images. Better quality and text than FLUX.1 Schnell, ~3× its cost. - [Nano Banana 2](https://docs.argil.ai/v2/models/nano-banana-2.md): Generate an image, or edit and blend up to 8 images, with Google Nano Banana 2 (Gemini 3.1 Flash Image). - [Lyria 2](https://docs.argil.ai/v2/models/lyria-2.md): Google Lyria 2 music generation. English prompts only, short instrumental clips (~30 s, WAV). Use Lyria 3 Pro for other languages or longer pieces. - [Lyria 3 Pro](https://docs.argil.ai/v2/models/lyria-3-pro.md): Google Lyria 3 Pro music generation (Preview). Longer instrumental pieces up to ~3 minutes, MP3; prompts in EN, DE, ES, FR, HI, JA, KO or PT. - [ElevenLabs Multilingual v2](https://docs.argil.ai/v2/models/elevenlabs-multilingual-2.md): ElevenLabs Multilingual v2: high-quality speech in 29 languages, from text or by converting a recording to another voice while keeping its delivery. - [ElevenLabs v3](https://docs.argil.ai/v2/models/elevenlabs-3.md): ElevenLabs v3 text to speech: more natural and expressive than Multilingual v2. - [ElevenLabs v4](https://docs.argil.ai/v2/models/elevenlabs-4.md): ElevenLabs v4 text to speech, the most expressive ElevenLabs model. Supports audio tags like [laughs] or [whispers]. - [ElevenLabs Turbo v2.5](https://docs.argil.ai/v2/models/elevenlabs-turbo-2-5.md): ElevenLabs Turbo v2.5 text to speech: low latency and half the price, for when speed matters more than peak quality. - [ElevenLabs English v2 (speech to speech)](https://docs.argil.ai/v2/models/elevenlabs-english-2.md): ElevenLabs English v2: says an English recording again with another voice, keeping its delivery. Lower latency than Multilingual v2. - [MiniMax Speech 02 Turbo](https://docs.argil.ai/v2/models/minimax-speech-2-0-turbo.md): MiniMax Speech 02 Turbo text to speech: fast, multilingual, good quality at a lower cost. - [MiniMax Speech 02 HD](https://docs.argil.ai/v2/models/minimax-speech-2-0-hd.md): MiniMax Speech 02 HD text to speech: higher quality than Turbo, multilingual. - [MiniMax Speech 2.5 Turbo](https://docs.argil.ai/v2/models/minimax-speech-2-5-turbo.md): MiniMax Speech 2.5 Turbo text to speech: the latest model, fast and multilingual. - [MiniMax Speech 2.5 HD](https://docs.argil.ai/v2/models/minimax-speech-2-5-hd.md): MiniMax Speech 2.5 HD text to speech: the latest model, highest quality, multilingual. - [Introduction](https://docs.argil.ai/pages/get-started/introduction.md): Welcome to Argil's API documentation - [API Credentials](https://docs.argil.ai/pages/get-started/credentials.md): Create, manage and safely store your Argil's credentials - [Quickstart](https://docs.argil.ai/pages/get-started/quickstart.md): Start automating your content creation workflow - [Introduction to Argil's Webhook Events](https://docs.argil.ai/pages/webhook-events/introduction.md): Learn what webhooks are, how they work, and how to set them up with Argil through our API. - [Video Generation Success Webhook](https://docs.argil.ai/pages/webhook-events/video-generation-success.md): Get notified when an avatar video generation completed successfully - [Video Generation Failed Webhook](https://docs.argil.ai/pages/webhook-events/video-generation-failed.md): Get notified when an avatar video generation failed - [Avatar Training Success Webhook](https://docs.argil.ai/pages/webhook-events/avatar-training-success.md): Get notified when an avatar training completed successfully - [Avatar Training Failed Webhook](https://docs.argil.ai/pages/webhook-events/avatar-training-failed.md): Get notified when an avatar training failed - [Get an Avatar by id](https://docs.argil.ai/api-reference/endpoint/avatars.get.md): Returns a single Avatar identified by its id - [List all avatars](https://docs.argil.ai/api-reference/endpoint/avatars.list.md): Returns an array of Avatar objects available for the user - [Create a new Avatar](https://docs.argil.ai/api-reference/endpoint/avatars.create.md): Creates a new avatar. - [Create an avatar from a video](https://docs.argil.ai/api-reference/endpoint/avatars.create.video.md): Video-based avatar creation is no longer supported - [List all voices](https://docs.argil.ai/api-reference/endpoint/voices.list.md): Returns an array of Voice objects available for the user - [Get a Voice by id](https://docs.argil.ai/api-reference/endpoint/voices.get.md): Returns a single Voice identified by its id - [Create a voice from audio](https://docs.argil.ai/api-reference/endpoint/voices.create.md): Creates a custom voice by cloning from an audio file. - [Sync voices from connected providers](https://docs.argil.ai/api-reference/endpoint/voices.sync.md): Re-syncs the voices imported from your connected ElevenLabs or Minimax provider accounts. - [Paginated list of Videos](https://docs.argil.ai/api-reference/endpoint/videos.list.md): Returns a paginated array of Videos - [Create a new Video](https://docs.argil.ai/api-reference/endpoint/videos.create.md): Creates a new Video with the specified details - [Get a Video by id](https://docs.argil.ai/api-reference/endpoint/videos.get.md): Returns a single Video identified by its id - [Delete a Video by id](https://docs.argil.ai/api-reference/endpoint/videos.delete.md): Delete a single Video identified by its id - [Estimate the credit cost of rendering a Video](https://docs.argil.ai/api-reference/endpoint/videos.estimate.md): Returns the credit cost of a render started right now, without debiting or starting one. The numbers match POST /videos/{id}/render. Creation costs (speech synthesis and other work already done while building the project) are not included. `newBalance` may be negative; this route still returns 200. - [Render a Video by id](https://docs.argil.ai/api-reference/endpoint/videos.render.md): Starts a render and returns the Video plus `renderCost`, the credits debited for this render (0 when the bundle was free). Quote the same number beforehand with GET /videos/{id}/estimate. Creation costs are not included. - [Retrieve all webhooks](https://docs.argil.ai/api-reference/endpoint/webhooks.list.md): Retrieves all webhooks for the authenticated user. - [Create a new webhook](https://docs.argil.ai/api-reference/endpoint/webhooks.create.md): Creates a new webhook with the specified details. - [Update a webhook](https://docs.argil.ai/api-reference/endpoint/webhooks.update.md): Updates the specified details of an existing webhook. - [Delete a webhook](https://docs.argil.ai/api-reference/endpoint/webhooks.delete.md): Deletes a single webhook identified by its ID. - [List Assets](https://docs.argil.ai/api-reference/endpoint/assets.list.md): Get a list of assets from your library - [Upload Asset](https://docs.argil.ai/api-reference/endpoint/assets.create.md): Upload an image or video asset via URL for use as B-roll - [Get Asset](https://docs.argil.ai/api-reference/endpoint/assets.get.md): Get an asset by ID with its current processing status - [Delete Asset](https://docs.argil.ai/api-reference/endpoint/assets.delete.md): Delete an uploaded asset - [List subtitle styles](https://docs.argil.ai/api-reference/endpoint/subtitles.list.md): Returns a paginated array of subtitle styles available for the user - [Export subtitles for a video project](https://docs.argil.ai/api-reference/endpoint/subtitles.export.md): Exports subtitles for a video project in VTT or ASS format. The subtitles can optionally include styling information. - [Getting started with Argil](https://docs.argil.ai/resources/introduction.md): Here's how to start leveraging video avatars to reach your goals - [Sign up & sign in](https://docs.argil.ai/resources/sign-up-sign-in.md): Create and access your Argil account - [Create a video](https://docs.argil.ai/resources/create-a-video.md): You can create a video from scratch or start with one of your templates. - [Pay-as-you-go credits explained](https://docs.argil.ai/resources/pay-as-you-go-pricings.md): Prices for additional avatars (clones and influencers) and credits purchases - [API - Pricing](https://docs.argil.ai/resources/api-pricings.md): Here are the pricings for the API - [Plans](https://docs.argil.ai/resources/subscription-and-plans.md): What are the different plans available, how to upgrade, downgrade and cancel a subscription. - [Create an avatar from scratch](https://docs.argil.ai/resources/create-an-avatar.md): There are two ways to create an avatar: a picture or a generation in the builder. Let's see the differences and how to create the two of them. We will also see how to pick your voice. - [Creating avatar styles](https://docs.argil.ai/resources/create-avatar-styles.md): What does it mean to add styles and how to add styles to your avatar - [Edit the style of your avatar](https://docs.argil.ai/resources/edit-avatar-styles.md): How to create different styles and variations for your avatar - [Copy the style of an image](https://docs.argil.ai/resources/copy-a-style.md): Transform any visual into your AI Avatar setup (clothes, background, etc.) - [Voice creation & Settings](https://docs.argil.ai/resources/voices-and-provoices.md): Configure voice settings and set up pro voices for your avatars and learn about supported languages. - [Prompt your own voice](https://docs.argil.ai/resources/prompt-a-voice.md): You can head to the Voices tab to create, from a prompt, the voice of your dreams - [Link a new voice to your avatar](https://docs.argil.ai/resources/link-a-voice.md): Change the default voice of your avatar - [Public avatars and pro avatars](https://docs.argil.ai/resources/create-your-own-ai-clone/public-avatars.md): What is the difference between normal public and pro avatars. - [Article to video](https://docs.argil.ai/resources/article-to-video.md): How does the article to video feature work? - [Product Visual](https://docs.argil.ai/resources/product-visual.md) - [Motion Control](https://docs.argil.ai/resources/motion-control.md): Transfer real movements from a video to your avatar - [Avatar actions](https://docs.argil.ai/resources/avatar-actions.md): You can now create your own medias and videos with VEO3 or Hailuo directly integrated into Argil using your own avatars or Argil's licensed avatars. It also integrates Nano Banana. - [Product Interaction](https://docs.argil.ai/resources/product-interaction.md): Show your avatar physically holding and using products - [Animate An Image](https://docs.argil.ai/resources/animate-an-image.md): Turn a single image into a short video with first and last frame - [Product Presentation](https://docs.argil.ai/resources/product-presentation.md): Create videos with an avatar presenting your product - [Story - Build an entire mini-film or ad](https://docs.argil.ai/resources/story.md): Build a multi-scene video from a single prompt - [Upload audio and voice-transformation](https://docs.argil.ai/resources/audio-and-voicetovoice.md): Get more control on the dynamism of your voice. - [Media and avatar layouts (positioning)](https://docs.argil.ai/resources/layouts.md): How to use split screen and different avatar positionnings - [Editing tips](https://docs.argil.ai/resources/editingtips.md): Some tips regarding a good editing and improving the quality of the video results - [Captions](https://docs.argil.ai/resources/captions.md) - [B-roll & medias](https://docs.argil.ai/resources/brolls.md) - [Music](https://docs.argil.ai/resources/music.md) - [Assets](https://docs.argil.ai/resources/assets.md): How do assets work, what type of files can be uploaded - [Account settings](https://docs.argil.ai/resources/account-settings.md): Issues with logging in (Google Sign up and normal email sign up) - [Managing Your Subscription](https://docs.argil.ai/resources/manage-plan.md): How to upgrade, downgrade and cancel your subscription - [Deleting your account](https://docs.argil.ai/resources/delete-account.md): How to delete your account - [Affiliate Program](https://docs.argil.ai/resources/affiliates.md): Earn money by referring users to Argil - [Create a Make automation with Argil](https://docs.argil.ai/resources/make-automation.md): Step by step tutorial on Make - [Contact Support & Community](https://docs.argil.ai/resources/contactsupport.md): Get help from the support and the community here - [Moderated content](https://docs.argil.ai/resources/moderated-content.md): Here are the current rules we apply to the content we moderate. ## OpenAPI Specs - [openapi](/openapi.yml) - [openapi](/v2/openapi.json) ## Optional - [Go to the app](https://app.argil.ai) - [Community](https://discord.gg/CnqyRA3bHg) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.