You can now create instant avatars from silent videos. Just upload a video without sound, and your digital twin is ready to go.

Check out our sizzling hot photo avatar templates for Halloween! Dive in and have a blast this Halloween!

Based on your feedback, we've updated more than 100 ultra-realistic voiceovers!

We've organized all our current voiceovers into 15 trending categories. It's now easier than ever to find your perfect voice.

We've squashed those pesky bugs in our checkout process. Now, you can expect a smoother and more secure checkout experience, guaranteed.

We've crafted these plans with companies in mind, offering generous usage limits and cost-effective solutions tailored for enterprise needs. Accessible through both our website and API, these plans are packed with benefits. Check out our pricing page for all the details and find the perfect fit for your business.

Beyond just human photos, DupDub AI can now breathe life into static animal images. Now, you can sync animal photos for lip-syncing, creating a whole new level of adorable and engaging content.

Expand your voiceover options with our Ultra service! We've added Vietnamese, Hungarian, and Norwegian to the mix, ensuring your audio comes alive with a wide range of authentic accents.

Tap into the magic of our AI Image feature. Just describe what you envision, and it'll bring your ideas to life with stunning visuals. Your creative journey is safely tucked away in your account. Harness its power to craft amazing creations, avatars, and videos that truly stand out.

Explore trending videos from different countries and localize them to your language and style. Utilize our transcription feature to obtain the original video scripts for translation or rewriting. Additionally, our video download feature allows you to gather video materials for your own content creation.

Introducing DupDub's Instant Avatar Cloning feature! Just upload a video, and we'll magically clone the avatar, capturing every nuance of their voice, facial expressions, and hand gestures. Dive into the future of digital representation and give it a spin today!

Tired of scrolling through pages of voices and listening to countless demos? Streamline your search with DupDub's intuitive voice search feature. Simply upload an audio clip, video file, or even a social media link, and we'll analyze the sound to find and match the closest voices in our library. It's that simple — no more endless browsing, just the voice you need, fast-tracked to your project.

With SSML, you have the flexibility to fine-tune your audio to perfection. Want to add a dramatic pause? No problem. Need to emphasize a particular word or adjust the pronunciation? Easy peasy. You can even control the speed of specific parts of your text. Say goodbye to one-size-fits-all voiceovers and hello to a personalized audio experience that's perfectly in tune with your vision.

Imagine being able to bring your creative vision to life with the perfect sound at your fingertips. No more sifting through libraries — just describe the sound you need, and our AI does the rest.

We've made significant enhancements to the lip-sync and facial expressions in avatar videos. Our ongoing commitment is to bolster the AI model's performance to deliver an even better experience for you.

Head over to your account settings by clicking "Update billing information" to make changes to your name, email, address, phone number, and tax ID whenever you need to.

Our AI Writing feature stands on its own as a powerful tool. Your entire interaction history is safely stored in your account. Explore its capabilities and craft outstanding copy that resonates with your audience!

When you're working with the voiceover feature in AI Avatar, you now have the option to dive into the advanced settings of your audio. It's not just about selecting a voice and tweaking its speed and pitch anymore. You can now add pauses, modify pronunciation, and more, giving you full control over your voiceover's nuances.

You can effortlessly incorporate subtitles into your avatar videos. Customize every aspect, from the font size, color, and position, to match your personal style.

Now you have the option to add DupDub to your desktop, allowing for convenient shortcuts and quick access.

Now you can translate videos in over 130 languages to Thai.

Sharper Face Detection: Our system now nails even the tiniest details on faces, making your avatars look spot-on.

Audio File Preservation: When you swap out a photo, your uploaded audio stays put, so you won't have to re-upload it.

Photo Enhancement: We've added a feature to give your photos a boost, making them look even better for your avatars.

Ultimate plan users can now create avatar videos that last up to 10 minutes. If you're on the Professional plan, you're good for 5-minute videos, and our Free, Personal and Pay-as-you-go plan users can upload up to 3 minutes. Dive in and make your avatar shine for longer!

The issue with the video effect for transparent photos has been resolved. Go ahead and upload your see-through background photos with confidence!

For our Instant Voice Cloning feature, we've added an auto-noise removal option. If your voice cloning file has background noise that might mess with the results, you can now choose to have us take care of that for you during the cloning process.

Users on our Professional and Ultimate plans can upload files of up to 60 minutes for transcription, while those on the Free and Personal plans can upload up to 20 minutes.

Get ready for a whole new level of interaction. Our gesture avatars not only sync their lips perfectly, but also come with lifelike hand movements!

Feel free to give it a spin and see for yourself how our video translation and dubbing turn out. It's on the house for now!

We've been all ears, taking in your feedback, and we've rolled out a fresh batch of voices that range from deep, rich tones to historical and animated characters—covering all the popular scenarios you've been using. Dive in and find your new favorite voice!

Now you can easily crop the photo and switch up its background color.

We'll keep a record of your AI-generated images, and you can download them all whenever you want.

You are free to navigate away from the page while the transcription is being done. We are constantly working hard to improve the efficiency of your workflow.

We've enhanced our language capabilities for over 40 Ultra voiceovers, now providing multi-language output in 29 languages. In addition to English, you can now access these voiceovers in languages such as Arabic, Bulgarian, Chinese, Croatian, Czech, Danish, Dutch, Filipino, Finnish, French, German, Greek, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Polish, Portuguese, Romanian, Russian, Slovak, Spanish, Swedish, Tamil, Turkish, and Ukrainian.

You can now customize the font size, color, background color, and position of subtitles in video translation API, allowing for a more tailored and inclusive viewing experience, catering to your diverse needs.

Adjusted the layout of AI avatar feature, optimizing its viewing and interaction on mobile devices.

We've enhanced the voiceover page with a mobile-friendly layout and design to be compatible with mobile devices. You can make masterpieces and check your projects more conveniently on your mobile now.

41 super natural large-language-model-based English voiceovers are now available online! You can choose from a variety of voice types and options to best suit your projects.

We are excited to announce that we now provide API access for all of our core features, including AI voiceover, AI avatar, AI transcription, video translation, and voice cloning. Developers can now easily integrate our AI capabilities into your applications and platforms by obtaining an API key through their personal account page.

Introducing a new linefeed-free mode for transcription results, offering a seamless and compact format for your transcribed content. This mode enables users to access transcription results without line breaks, facilitating easier processing and readability.

We've added a new 3D avatar feature in addition to the 2D photo avatars. You can make and personalize your own 3D avatars, picking from different clothing, hairstyles, and accessories that are already pre-made. Give it a try in your video editing projects to give your content a more unique feel!

We've adapted our transcription feature for top-notch performance on mobile devices. Now you can transcribe videos on your phone more conveniently.

We've improved the success rate of AI voiceover generation by refining algorithms and leveraging advanced technologies.

Streamline the structure and enhance the user interface to improve the overall experience of Video editor.

Enhance onboarding process of key features to make it more intuitive and streamlined for new users.

DupDub Apps Now on Canva! Enable you to effortlessly incorporate avatars and voiceovers into your Canva videos. Simply search for Avatars by DupDub and AI Voice by DupDub on Canva.

Several bugs have been resolved! Delight in the flawless text-to-speech editor.

Translate videos effortlessly with just one click. No need to worry about manual translations, voiceovers, or synchronizing subtitles!

Now you can easily keep track of your credit usage and monitor your purchases.

We offer automated transcription and translation support for your convenience. When you choose the spoken language of the uploaded audio or video, we will transcribe the content for you. If you choose a different language, we will not only transcribe the script but also provide a complete translation!

Introducing Voiceovers in Tamil, Urdu, and Marathi! Give them a try and experience the magic!

Now you can easily save your transcription history! No need to worry about missing any previous files.

We've added some awesome features and improvements to make your experience even better! Now you have auto captioning, multi-character talking avatars, AI Photo Enhancer, expanded text character limits for paid users, and performance improvements. Enjoy the enhanced experience!

We're excited to announce that we have gone above and beyond to optimize our text to speech voice editor with a brand new interface and experience. Get ready to immerse yourself in an enhanced audio journey like never before! 👉 Try the new "Multiple voiceover" mode to effortlessly add multiple voiceovers!

Introducing our groundbreaking AI tools that revolutionize video localization. With our three powerful features - Transcription, Translation, and AI Voiceover - achieving seamless video localization has never been easier. Convert speech into accurate text, then translate your text into multiple languages, and transform your translated content into professional and realistic voiceovers to reach a wider audience.

We've conducted comprehensive testing and fine-tuning to ensure optimal performance and reliability of transcribing subtitles from social links.

We have introduced an online chatting service to provide you with prompt and convenient support. You can ask your questions and get instant answers without having to wait for emails!

Exciting news! We are pleased to announce the launch of our referral program. Invite your friends to join and earn generous credits up to 462!

Choose from over 50 languages for transcription. Easily convert your audio and video into text and subtitles in English, Spanish, Portuguese, French, Italian, Russian, Chinese, Tagalog, Thai, Vietnamese, and many others.

A revolutionary advancement in text-to-speech technology that delivers super realistic quality! Immerse your audience in an unparalleled auditory experience with life-like and emotive voiceovers that are indistinguishable from actual human speech!

The DupDub team is open to all users. Join the user interview to earn a 50% OFF discount coupon!

Click on the subtitles directly within the video preview section to customize subtitles in our video editor!

Support importing SRT subtitle files in the video editor. Easily enhance your videos by seamlessly importing subtitles with just a few clicks.

Multi-character talking photo: Witness the unparalleled innovation as we proudly become the pioneers in enabling dynamic conversations across multiple characters in talking photo!

AI avatar generation: By simply entering a prompt, you can now generate stunning AI avatars that bring your ideas to life!

Lightning-fast generation and refresh: We've worked diligently to enhance the generating and refreshing time, ensuring a seamless and uninterrupted experience.

Discover a wide array of AI tools at your fingertips! Navigate effortlessly to find the ones that suit your needs. Explore our incredible selection of Talking Photo templates and access our handy tutorials whenever you require assistance!

Showcase your creativity on TikTok using the DupDub Talking Photo feature, and stand a chance to win amazing cash prizes and DupDub credits!

Elevate your Talking photo experience with an enhanced interface.

We've fixed the annoying bugs in our text to speech editor, ensuring a smooth and hassle-free experience.

Indulge your creative spirit with AI-powered content creation experience, combining captivating storytelling and powerful editing tools -- Idea to text, Text to speech, Text to video, and Video editing. Streamline your workflow today!

Expand the available fonts for video editing by incorporating an impressive collection of over 20 diverse and dynamic typographies.

Step into a whole new level of storytelling with DupDub AI talking photo feature. Want your dull images and avatars to break their silence? Make photos come to life with words as if they’re born to tell stories!

The corresponding subtitles will be displayed on the audio track when converting text to speech.

Now our voice cloning service is available in English, Spanish, Portuguese, French, Thai, Japanese, Korean, Malay, Finnish, and Turkish. See demo and try it today!

Make it more convenient for users to create subtitles and videos, eliminating concerns about misalignment issues between the original video/audio and the subtitles.

Experience more transitions and effects supported in Video Editing. Come and give it a try!

Weave your narrative and uncover the magic of ALL-IN-ONE and FULL-FEATURED Content Creation Platform! Our vision is to help content creators increase efficiency and reduce costs through innovative technologies and our user-friendly tools.

Transform the way you create content with DupDub AI - Your Ultimate content creation Assistant!

Enhancing editor functionality to include comprehensive support for Arabic languages, ensuring seamless typing, editing, and listening experiences.

Speed up the processing time of audio and video transcription, enhancing efficiency and reducing time.

Transform written words into natural-sounding, high-quality voices and enhance the accessibility and inclusivity of your digital content with our Text-to-Speech API.

Experience the ultimate freedom in voice technology and unlock endless possibilities by trying voice cloning!

We have elaborated everything on Help Center, including tutorials, pricing explanation, etc.

Target languages of Translation feature increased from 22 to 36. You can turn the translated text to speech with a few clicks.

No credit card required! Try all features on DupDub with no commitment!

Some DupDub voiceovers are improved to 48k high-quality sound.

Set the default voiceover with the proper language according to your country\'s official language when you first use Voice Editor.

Set the voiceover with the target language you select in Translation when you use "Convert text to speech" of Translation feature.

4 use cases, including demo audios and videos, are updated on our website! Find your case and try DupDub for free!

We have listed DupDub on Appsumo——$69 to buy a lifetime plan! Use DupDub as you need and don\'t worry about the period of validity!

Follow or join DupDub social media networks (Facebook/Facebook Community/Twitter/Instagram/YouTube) and win 1-month FREE membership!

New year special offer is on sale! 20% off for all plans! Ends at any time!

Launch 10 new languages: Afrikaans, Czech, Danish, Dutch, Finnish, Hungarian, Norwegian, Polish, Swedish, Turkish.

Support importing text from files! Text files(txt, doc, pdf), audio/video files(wav, mp3, mp4) and video links(YouTube, TikTok, Facebook) are all available.

Launch Translation feature -- converting source language text into 10+ targeted languages audios with only 2 steps.

Optimize the UI and UX of Transcription, Subtitle alignment and YouTube downloader.

Answer 3 questions to get 3 download chances!

Big revision of our homepage! Try our worldwide AI voices!

Upload experience optimization for Transcription and Subtitle alignment

Export experience optimization for Text to Speech.

Launch beginner\'s guide for Text to Speech editor.

Launch homogragh, supporting quick-choose the pronunciation of a heteronym.

Support detecting the language of entered text and selected voiceover, so as to recommend users a suitable voiceover if not paired.

More voices in German, French, Italian, Indonesian, and Spanish launched. 280+ voices and 380+ styles are supported in Voice Store.

Filipino Language, together with 10 alternative voices, launched.

Launch new function of Lexicon, which supports user-defined input of Alias Lexicon and Phoneme Lexicon.

Multilingual voices launched, such as German, French, Italian, Indonesian, and Spanish. 180+ voices and 280+ styles are included in Voice Store.

Optimize Editor shortcuts to help position the punctuations, words, sentences and paragraphs, to enable better efficiency.

Optimize Editor shortcuts to help position the punctuations, words, sentences and paragraphs, to enable better efficiency.

Google Pay and Apple Pay, as another two alternative payment methods.

Support Transcription and YouTube downloader from Facebook/Twitter/TED.

More emotional voices online. 150+ voices and 180+styles are supported in Voice Store.

Optimize the editing features of finding and replacing Alias and Phoneme in batch mode.

Launch new editing feature of Alias.

Speed up the editing efficiency and the limit of characters has been up to 30,000.

Fix the slow loading of the speakers\' avatars.

Remove the limits of 100M and 300M in Transcription and Subtitle alignment.