
Qimiaoyuan is an AI digital human short-video and livestreaming solution launched by Mobvoi. With this digital avatar creation and livestreaming platform, users can create their own digital avatars and conduct livestreaming activities through them. The Qimiaoyuan platform currently has more than 100 digital humans and more than 1,000 3D digital assets, providing users with a wide range of choices.
About
Overview
Qimiaoyuan is a one-stop AI digital human short-video and livestreaming platform launched by Mobvoi. It is designed for content creators, brands, and enterprise users, providing complete capabilities from digital avatar generation to video production and livestreaming applications. The platform connects content production workflows such as AI writing, AI painting, AI voice dubbing, and digital human video production, helping users reduce the costs of appearing on camera in person and repeated recording.
Qimiaoyuan supports multiple digital avatar solutions, including single-photo driving, 2.5D real-person cloning, 3D digital human customization, and enterprise IP character activation. According to official information, the platform has 100+ digital humans and 1000+ 3D digital assets, which can meet the needs of various scenarios such as short-video production, brand promotion, virtual hosts, and corporate training.
Key Features
-
Real-person avatar cloning
Create a drivable digital human through photos or avatar materials. After entering text, a digital human talking-head video can be generated, suitable for scenarios such as knowledge sharing, marketing explanations, and product introductions. -
Text-driven digital human speech
After users enter copy, the digital human can automatically complete spoken output and present relatively natural lip movements, expressions, and speaking rhythm. -
Voice cloning and AI dubbing
Supports text-based speech synthesis and provides a relatively rich selection of voice timbres and expressive styles. According to public information, the platform supports 600+ voice options, 16 languages, 15 regional dialects, and multiple emotional expressions. -
3D digital human customization
Supports high-precision 3D digital human production for scenarios such as livestreaming, virtual hosting, brand endorsement, and exhibition hall display. -
Enterprise IP character activation
Existing enterprise IPs or brand characters can be upgraded into digital avatars that can "speak and move" for brand communication, event promotion, and content matrix building. -
Digital assets and editing capabilities
The platform provides a large number of digital humans, templates, and 3D assets, and supports online editing, lowering the barrier to video production.
Pricing
-
Free Version
Available for free, supports 30-second video synthesis, and provides some free digital humans, voices, and template resources. -
Monthly Plan: 298 yuan/month
Supports a cumulative 30 minutes of video synthesis, with unlimited use of digital humans, voices, templates, and assets. -
Annual Plan: 2499 yuan/year
Supports a cumulative 360 minutes of video synthesis, with unlimited use of digital humans, voices, templates, and assets.
Frequently Asked Questions
What model capabilities is Qimiaoyuan based on?
Qimiaoyuan is based on Mobvoi's self-developed large model "Sequence Monkey", covering tasks such as text generation, image generation, 3D content generation, speech generation, and speech recognition.
What languages and voice types does Qimiaoyuan support?
According to public information, the platform supports more than 600 voice options, 16 national languages, 15 regional dialects, and multiple emotional expressions, making it suitable for cross-language and multi-style content production.
What digital human assets does Qimiaoyuan provide?
The platform provides nearly 100 AI digital humans in different styles, covering different ages, professions, and character types, while also supporting online face customization for 3D digital humans and customized avatar creation.
What usage scenarios is Qimiaoyuan suitable for?
It is suitable for scenarios requiring large-scale, low-cost video content production, such as short-video talking-head content, virtual livestreaming, corporate promotion, brand IP operations, education and training, and e-commerce explanation.
Related Tools
View allWondershare Filmora 2023 is a domestic video editing software that is easy to use and feature-rich, supporting one-click import of SRT subtitles, with a simple and stylish interface, flexible timeline editing functions, and abundant resource effects.
MyVocal.ai is a tool that provides voice synchronization and voice cloning features. Users can synchronize their own voice with popular music and complete voice cloning in a relatively short time.
Pod Genie is an AI podcast tool that can convert RSS feeds into personalized podcast content, and provides customized news broadcasts, newsletters, and summary services, making it convenient for users to access audio information based on their interests.
Lovo is an AI voice generation and text-to-speech tool that supports converting text into natural speech, suitable for audio content production, voiceover, and various creative scenarios, helping reduce manual recording costs and time investment.
YouWhisper is a machine-learning-based video production and editing tool for users who need to quickly process video footage, offering multiple editing options to help create higher-quality video content.
Mubert is an AI music generation tool that provides royalty-free tracks for content creators and app developers, and can generate music by style, mood, use case, and duration.
