🎯 Frequently Asked Questions

Please make sure to check before submitting your video! Since AI Avatar is trained based on the videos you submit, the quality of the videos directly affects the quality of the avatar. ✅ High-quality sources create high-quality avatars! You must provide a video with a resolution of 4K (3840×2160) to create a 4K quality avatar. 1080p video, final avatar also supports up to 1080p. The higher the resolution of the original, the better the expression of details such as mouth shape, facial expression, and texture. 📸 Tip: Enable 4K video recording setting on iPhone Pro, latest Galaxy, mirrorless cameras, etc. 🎥 Recommended video composition example (1 minute) 📍 Intro (5 seconds) Please look at the camera as if you were talking to a conversation partner. The key is to maintain a natural listening posture. I like it when your eyes and facial expression make it seem like you're listening to someone else's story. ✨ Point: Create a sense of stability by not moving, maintaining a fixed gaze, and subtle changes in facial expression. 🗣️ Main Speaking (45~50 seconds) Please look at the camera and speak confidently. You can choose a free topic (self-introduction, interests, favorite topics, etc.) Keep your body as still as possible and focus on your face when speaking. Clear and crisp pronunciation + maintain the speed of speech at the level of normal conversation 😊 Ending (5 seconds) After you finish speaking, look at the camera and smile gently. It is important to finish in a natural still position.

1️⃣ 🎥 Easy and fast video upload You can create a perfect AI clone Avatar in just 1 minute of video! ✅ Video upload conditions Length: 1 minute or more to 5 minutes or less Format: .mp4 Content: The user's face and voice must be included. Recommended resolution: 720p or higher (optimal: 1080p ~ 4K) 👉 [📹 View the shooting guide] Please also check out our guide to submitting high-quality footage, including lighting, costumes, backgrounds, and audio. 2️⃣ 🛠️ AI Clone Avatar Production After receipt, an internal review and production process will be conducted. 🧠 Production Information Target: Subscribers with Enterprise plan or higher Production period: Approximately 3 to 4 days Voice Synthesis: Applying Voice Cloning with ElevenLabs Lip Sync: Advanced lip sync technology makes it sound like you're speaking in real life 📌 Summary of internal processes Confirmation of receipt and review of suitability Voice Extraction and Cloning Video learning and template creation Create an avatar thumbnail image

🎬 What's in AI Studio? PERSO AI Studio is a web-based video editing tool. You can upload a PPT file, configure scenes for each slide, and edit the video by loading a script. Automatically converts slide to scene structure What is written in the slide notes = automatically applied as a script Complete the video by selecting AI Avatar + TTS [Example of use] 🧑‍🏫 What about AI Presenters? AI Presenters is a plugin available in PowerPoint's 'Add-ins'. You can search for PERSO AI Presenters in the [Home → Additional Features] menu. 30 models of AI Avatar provided by Studio Create a video within a slide after writing the language/voice/script The generated video can be inserted into PPT and used as a presentation object. [Example of use] 🔍 Try using it like this! If you want to upload PPT and create video content? → AI Studio What if you want to visualize your presentation right away while making it with PPT? → AI Presenters 💡 AI Presenters can be tried for free for 3 minutes by anyone without installation. 📁 If you need advanced editing features of Studio, continue working in the web-based Studio!

PERSO offers a variety of subscription plans to suit your needs. Each plan differs in credit amount, team features, resolution options, and the ability to purchase additional credits. 💡 Comparison of key features by plan Flan Credit amount paid Additional credits can be purchased Supports 4K resolution Invite team members Free 3 Credits (given upon sign-up) ❌ ❌ ❌ Creator 15~60 credits (plan selection available) ✅ ❌ ❌ Team 90~300 credits (plan selection available) ✅ (Only owners can purchase) ❌

AI Studio is not just a simple video editing tool! A completely new AI-based video production solution with powerful features: 🔹 Key features of AI Studio ✅ 📢 Supports over 148 languages – Speak naturally in multiple languages using MS-TTS ✅ 🎭 Variety of AI Avatar & Outfits – 100+ models and custom styles to choose from ✅ 📷 High resolution support – Clear and natural expressions like a real person ✅ 🔄 Left/right side setting possible – Supports side presentation as well as front view ✅ 🎬 AI Avatar Chat feature – Create conversations between two AI Avatar in one video ✅ 🎨 Background settings & text effects – Apply desired background and subtitle style ✅ ⏳ Create videos without filming – Create AI Avatar content quickly without separate filming 🔹 What if you use AI Studio? 📚 Online lecture → Even if the instructor is not present in person, AI Avatar explains 🛍️ Shopping Guide Video → Deliver product information more naturally and attractively 📢 Corporate promotional video → Easily create professional videos without separate filming 🎓 Educational content → Providing professional and friendly lectures using AI Avatar 🎥 Anyone can easily create professional-level videos!

To ensure the quality of the dubbing function, it is important to meet the following conditions: 1️⃣ How much voice volume is needed for AI dubbing? Each speaker's voice must be included for at least 20 seconds. If the speech time is too short, the accuracy of translation and voice generation may be low. 2️⃣ What is the optimal number of speakers? Currently, we support seamless dubbing for up to two speakers. Audio is supported even in videos with multiple speakers, although voice cloning and speaker separation features may vary somewhat. 3️⃣ Background sound and sound effects processing If the background music includes sound effects made by people (e.g. laughter), they are currently not filtered separately. Therefore, sound effects can also be recognized as normal speech and translated. 4️⃣ Processing images in noisy environments and fast speech In noisy environments (train noise, cicadas, background music, etc.), the accuracy of speech recognition and translation may be reduced. If it contains fast speech (including fast-forwarded video), it may not work properly. If you meet these conditions, you can experience more stable voice translation quality. 😊

🎥 PERSO AI Dubbing This one video is all you need! AI can translate subtitles and even do voice dubbing? Quickly learn how to create global content without language barriers with our AI Dubbing tutorial video 🌍✨ [ENGLISH version] [KOREAN version]