> For the complete documentation index, see [llms.txt](https://docs.avis.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.avis.net/guide/console/playground.md). # Playground The Playground lets you try AVIS models in your browser without writing code or creating an API key. Use it to compare models, test prompts, and get a feel for output quality and cost before you build. Open it from **Playground** in the Console sidebar. **Note:** Generations in the Playground are paid from your credit balance, just like API calls. Your current balance is shown in the top-right corner of the Playground. *** ## Layout The Playground has two areas: * **Left panel:** choose a mode (**Image**, **Video**, **Audio**, or **Chat**), pick a model, write your prompt, and adjust settings. * **Right panel (Creation):** every result you've generated, newest first. Use the filter icons at the top right to show all results or a single media type, and switch between grid and list view. *** ## Generate an image **Step 1:** Select the **Image** tab. **Step 2:** Click the model name to open the model list. Type in the search box to find a model quickly, and select it. The model ID appears under each name. **Step 3:** Describe the image you want in the prompt box. **Step 4 (optional):** Click **Reference** to upload an image the model should use as a starting point or style guide. Turn on **Multi Shot** to generate a set of related images in one go. **Step 5:** Click the settings bar above **Generate** (for example **1K, 16:9, 1**) to adjust: * **Mode:** output resolution, such as **1K** or **2K** * **Ratio:** aspect ratio, from 1:1 to 21:9 * **Output:** how many images to create, from 1 to 8 **Step 6:** Click **Generate**. The result appears in the **Creation** panel when it's ready. **Tip:** Each extra output is billed separately. Start with **Output: 1** while you're refining a prompt. *** ## Generate a video **Step 1:** Select the **Video** tab and choose a video model. **Step 2:** Optionally upload a **start frame** and/or **end frame** image, a **Reference** image, or an audio reference. Supported references can be images, videos, or elements, depending on the model. **Step 3:** Describe the scene and the motion you want. **Step 4:** Click the settings bar (for example **720p, 5s, 16:9, Sound: On**) to choose resolution, duration, aspect ratio, and whether to generate sound. **Step 5:** Click **Generate**. Video takes longer than images, so you can keep working while it renders. **Note:** Video is billed per second of output, and higher resolutions and sound cost more. Check the price for your settings on the [Pricing](https://www.avis.net/pricing) page. *** ## Generate speech or audio **Step 1:** Select the **Audio** tab and choose an audio model. **Step 2:** Type or paste your script (up to 3,000 characters), or click **Import** to load one. You can add direction inside the script: * `@` to assign a voice to a line * `[laughs]` or similar tags for emotion * `[pause 0.5s]` to add a pause **Step 3:** Use **References** to provide a voice sample, if the model supports it. **Step 4:** Adjust **Tone**, **Speech Rate**, and **Volume**, then click **Generate**. *** ## Chat with a text model **Step 1:** Select the **Chat** tab and choose a model. **Step 2:** Type a message in the **How can I help?** box and press the send button. Use **+** to attach a file or image, if the model supports it. You can also start from one of the suggested tasks below the message box, such as content moderation, social media captioning, object grounding, or info extraction. *** ## What's Next * Found a model you like? Copy its ID from [Models](/guide/console/models.md) and use it in your code, see [Make your first API call](https://github.com/coin98/documentation/tree/docs_avis/guide/console/first-api-call.md). * Building multi-step creative work? Try [AVIS Creative Studio](/avis-creative-studio/getting-started/what-is-avis-creative-studio.md), where you can chain models on a visual canvas. *** ## FAQ ### Does the Playground cost the same as the API? Playground generations are paid from the same credit balance. Your Dashboard shows them separately as **AVIS Playground** usage, so you can tell them apart from API calls. ### What happens if a generation fails? The card shows **Generate failed**. You aren't charged for failures caused by the model provider. If the failure was caused by your input, such as a prompt rejected by the model's content filter, you may be charged for work already done. See [API Pricing & Fees](/guide/get-started/api-pricing.md). ### How long are my results kept? Generated files are stored for a limited time. Download anything you want to keep. ### Do I need an API key to use the Playground? No. You only need to be signed in and have credits. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.avis.net/guide/console/playground.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.