Jump to content

Draft:QashqAI Voice

From Wikipedia, the free encyclopedia
  • Comment: Please add reliable and independent references to the topic. Fade258 (talk) 06:24, 26 June 2025 (UTC)

QashqAI Voice is an open-source, multilingual AI initiative focused on preserving endangered languages and promoting digital inclusion, especially for marginalized communities such as visually impaired users, refugees, and stateless speakers.

The project was founded by Siefollah Aslani, a Bremen-based activist and language preservation advocate, in 2025.It combines speech-to-text (STT), large language models (LLMs), and text-to-speech (TTS) technologies to support voice interaction in minority languages, such as Qashqai Turkic, Persian, and rural dialects.

Goals

[edit]

- Preserve endangered languages using modern AI. - Enable accessibility for low-literacy and visually impaired populations. - Provide free tools for cultural self-expression via speech and translation. - Empower migrants and refugees in their native voices.

Technologies

[edit]

The platform uses OpenAI's Whisper for speech recognition, GPT models for language generation, and various open-source TTS engines. It is designed for low-bandwidth access and non-commercial use.

Recognition

[edit]

QashqAI Voice has been acknowledged by OpenAI support teams, and submitted for review by the UNESCO Secretariat under the 2003 Convention for the Safeguarding of the Intangible Cultural Heritage.

[edit]

See also

[edit]
  • Qashqai people
  • Language preservation
  • Assistive technology