Vietnam · Hanoi · See the Vietnam profile · See the Hanoi profile
Top 98% 32/100 · Ask Evidence Copilot about this practice
UNICEF Viet Nam and ATscale launched 'vi vu', Vietnam's first natural Southern-dialect Vietnamese text-to-speech voice — a free, open-source AI voice that plugs into existing screen readers and AAC apps to widen digital access for blind and low-vision users.
Vietnamese text-to-speech engines exist, but before mid-2024 none offered a natural-sounding Southern Vietnamese dialect voice — leaving screen-reader and AAC (augmentative and alternative communication) users in southern Vietnam with a less natural experience than users of the Northern dialect that dominates commercial voice products.
In July 2024, UNICEF Viet Nam, working with UNICEF headquarters and ATscale (the Global Partnership for Assistive Technology), commissioned developer LouderPages to build 'vi vu', an AI-generated Southern-dialect voice. It is distributed as a free, open-source download compatible with Android, Linux and Windows, designed to plug into existing screen readers, e-book readers and AAC software rather than requiring a new standalone app.
Coverage from UNICEF, ATscale and Vietnam's state news agency (VietnamPlus) confirms the launch and technical design, but none of the available sources report post-launch adoption figures, download counts, or a formal usability evaluation with blind or AAC users — a genuine gap in the public evidence at this early stage.
Read the full analysis: https://en.vietnamplus.vn/ai-based-vietnamese-language-voice-solutions-launched-post176181.vnp
Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.
Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.
Where this practice's information was retrieved from, and when.
United States of America
Microsoft's free Immersive Reader applies specific, peer-reviewed reading-science findings — on font spacing, syllable breaks, line length and text-to-speech — …
Paraguay
UNICEF, Paraguay's Ministry of Education and Paraguay Educa adapted school textbooks into accessible digital formats — audio narration, sign-language video, …
Israel
Israeli company Voiceitt built an AI speech-recognition engine trained on atypical and dysarthric speech, letting people with severe speech impairments …
Serbia
Serbian startup SignAvatar deployed 'TransportSign' at Belgrade's Central Railway Station, using AI to convert real-time public-transport announcements into sign-language avatar …
Open full copilot Grounded in cited practices — always check the sources.