# CellCog Avatars Guide Avatars are digital personas you build from reference images, a cloned voice, a sample talking video, and a personality, so agents generate consistent content featuring the same character or person every time. --- ## What Are Avatars? An avatar can carry any combination of: - **Images**: reference photos for visual consistency - **Voice**: a cloned voice for speech generation - **Sample Video**: a short clip of the person talking, so generated videos match their real voice, talking style, and expressions - **Personality**: traits and a communication style Use an avatar in any chat by naming it: "Using avatar [name], create..." The agent pulls in the avatar's details automatically. --- ## Accessing Avatars Open the **More** menu at the bottom of the sidebar and click **Avatars**. --- ## Creating an Avatar 1. Go to **Avatars** 2. Click **Create Avatar** 3. Fill in the details: - **Avatar Name** (required, unique among your avatars) - **What is this avatar for?**: Brand Mascot, Digital Twin, Creative Character, or Other - **Describe your avatar's purpose** (optional) - **Where will you use it?**: Website, Social Media, Customer Support, Marketing & Ads, Video Content, Podcasts & Audio, Games & Interactive, Internal/Training, Other (optional) - **Personality Traits** (select up to 5) and **Communication Style** (optional) 4. Click **Create** After creation, the avatar page opens with tabs for **Images**, **Voice**, **Sample Video**, and **Personality**. --- ## Avatar Use Cases | Use Case | Description | |----------|-------------| | **Brand Mascot** | Represent your brand or company | | **Digital Twin** | Represent yourself or a real person | | **Creative Character** | Comic, anime, or fictional character | | **Other** | Something else | --- ## Adding Images Images help maintain visual consistency across generated content. An avatar holds up to **10 images**. 1. Open your avatar and go to the **Images** tab 2. Click **Upload Image** 3. Choose a PNG, JPG, or WebP file (max 10 MB) 4. Give it a **Label** (for example, Default, Happy, Professional) and an optional **Description** so agents know when to use it 5. Optionally tick **Set as Primary Image** (the main reference) No photos yet? **Create Image** (or **Create First Image**) starts a chat where an agent generates reference images for the avatar. **Best practices:** - Use clear, high-quality images - Include different angles and expressions, labeled clearly - Mark your best image as primary --- ## Adding Voice Clone a voice to use in speech generation. Each avatar holds one voice; delete the existing voice before adding a new one. Before cloning, you tick a consent box confirming the voice is yours (or that you have the person's written consent) and agreeing to how the sample is processed and kept. Deleting the voice removes the recording, the generated sample and the voice model at our voice provider. 1. Open your avatar and go to the **Voice** tab 2. Click **Upload or Record Voice Sample** 3. Upload an MP3, WAV, OGG, M4A, or AAC file (max 25 MB, at least 10 seconds), or record directly in the browser (at least 10 seconds) 4. Click **Clone Voice** 5. Processing typically takes 2 to 5 minutes; you can close the window and come back **Recording tips:** - Use a quiet environment - Speak naturally and clearly - Include varied sentences; longer, cleaner samples give better clones When processing finishes, the tab shows **Voice Ready** and you can play the original recording and a generated sample. If cloning fails, the tab shows **Voice Failed**; delete the voice and try a cleaner recording. Don't have a recording? **Design Voice** starts a chat where an agent helps you create a voice instead. --- ## Adding a Sample Talking Video A sample video grounds generated videos in the person's real voice, talking style, and facial expressions instead of imagining them from a still image. 1. Open your avatar and go to the **Sample Video** tab 2. Click **Upload Sample Video** 3. Upload an MP4 or MOV clip of the person speaking naturally to camera: 10 to 15 seconds recommended, 5 to 30 seconds accepted, max 200 MB 4. The duration is checked on upload; clips outside the accepted range are rejected Uploading a new sample replaces the previous one. Use **Delete Sample Video** to remove it. --- ## Adding Personality Define how your avatar communicates. 1. Open your avatar and go to the **Personality** tab 2. Click **Edit Personality** 3. Set: - **Personality Traits**: pick up to 5 from Professional, Casual, Friendly, Formal, Witty, Empathetic, Authoritative, Playful, Calm, Energetic, Helpful, Creative, Analytical, Warm, Direct - **Communication Style**: a description of how they speak or write 4. Save changes **Example:** - Traits: Professional, Warm, Helpful - Style: "Speaks confidently but warmly, uses simple language, avoids jargon" --- ## Using Avatars in Chats ### Basic Usage Include your avatar's name in your prompt: > "Using avatar Luna, create a video introducing our new product" > "As avatar Alex, write a blog post about AI trends" Or click **Create Content** on the avatar's card or page to start a chat with the avatar already selected. ### What Happens When you reference an avatar: 1. The agent loads the avatar's details (images, voice, sample video, personality) 2. Generated images use the avatar's likeness from its reference images 3. Speech and narration use the avatar's cloned voice 4. Generated videos use the sample video to match the person's real voice, talking style, and expressions 5. Written content matches the avatar's personality --- ## Avatar Status Each avatar shows a status on the Avatars page: | Status | Meaning | |--------|---------| | **Ready** | Has at least one of: images, voice, sample video, or personality | | **Processing** | Voice is being cloned | | **Incomplete** | No images, voice, sample video, or personality yet | | **Failed** | Voice cloning failed; delete the voice and re-upload | --- ## Editing an Avatar 1. Open the avatar 2. Click **Edit** (top right) 3. Modify details 4. Save changes You can update the name, use case and purpose, target platforms, and personality traits and style. Images, voice, and sample video are managed from their own tabs. --- ## Deleting an Avatar 1. Open the avatar 2. Click **Delete** (top right) 3. Confirm **Warning:** This permanently removes the avatar and all associated images, voice (including the voice model at our voice provider), sample video, and settings. --- ## Example Workflows ### Creating a Brand Spokesperson Video 1. Create an avatar with your spokesperson's details 2. Upload several reference images from different angles 3. Upload a 10 to 15 second sample video of them talking to camera 4. Add a voice sample 5. In a chat: "Using avatar [name], create a 30-second product announcement video" ### Generating Consistent Character Art 1. Create an avatar for your character 2. Upload character reference images with descriptive labels 3. In a chat: "Using avatar [name], create an illustration of them in a coffee shop" ### Voiceover and Narration 1. Create an avatar with a voice sample 2. Define its communication style 3. In a chat: "Using avatar [name], narrate this script: [your script]" --- ## Frequently Asked Questions ### How many avatars can I create? There's no set limit on the number of avatars. Each avatar holds up to 10 images, one voice, and one sample video. ### Can I use someone else's likeness? Only create avatars of yourself or characters you have rights to. Don't create avatars of others without permission. ### How long does voice processing take? Usually 2 to 5 minutes. You can leave the page while it processes. ### Why does my avatar show "Incomplete"? It has no images, voice, sample video, or personality yet. Add any one of them and the avatar becomes Ready. ### Can I share avatars with team members? Avatars are personal to your account. Team members need to create their own. ### What if voice cloning fails? Delete the failed voice and upload a cleaner sample: - Minimal background noise - Clear speech - At least 10 seconds; longer is better ### What makes a good sample video? One person, facing the camera, speaking naturally for 10 to 15 seconds, with clear audio. The clip must be between 5 and 30 seconds. --- ## Related Guides - [Getting Started](./CellCog_Getting_Started.md) - [Chat Guide](./CellCog_Chat_Guide.md) --- Markdown alternate of https://cellcog.ai/support/avatars-guide (CellCog support guide, category: Features). All guides for agents: https://cellcog.ai/support/llms.txt. Site index: https://cellcog.ai/llms.txt. Try CellCog free, no credit card needed: https://cellcog.ai/signup