DESKTOP SOFTWARE · IN DEVELOPMENT

Video that speaks to more people.

AI-assisted video localization, with the editor in control. XichQuy Studio is developing a desktop environment for subtitles, translation, voice, and the final edit.

Explore the product See the workflow

Independent project. Work in progress.
Human judgment stays at the center.

Illustrative workspace concept · not an application screenshot
ONE VIDEO. MANY CONNECTED DECISIONS.

Recognize Translate Voice Review

01 / PRODUCT DIRECTION

A workspace for
the whole conversation.

Words, voices, and time belong together. Our desktop product direction aims to bring the details of localization into a more organized environment.

ILLUSTRATIVE INTERFACE CONCEPT
This is a visual study, not a capture of the application. The panels illustrate a proposed workflow; they do not establish that the depicted controls or integrations are implemented.
A

Keep the source in view

The concept places video beside text so wording can be considered in its original visual context.

B

Make timing visible

Aligned video, subtitle, and voice tracks show the relationships an editor needs to examine.

C

Leave room for judgment

Review notes represent the human checks that recognition and generation cannot settle alone.

02 / DEVELOPMENT AREAS

From the first word
to the final frame.

Six connected areas of exploration. These describe project scope, with capabilities and availability still being evaluated.

READ THE SOURCE01

Subtitle OCR

Explore extracting text from subtitles embedded in video frames, with room to inspect and correct recognition results.

On-screen text → editable subtitle drafts
READ THE SOURCE02

Speech Recognition

Develop speech-to-text workflows that turn spoken dialogue into a text track for editing and review.

Spoken dialogue → transcript drafts
ADAPT THE CONTENT03

Translation

Explore adapting recognized text across languages while preserving meaning, context, and the editor’s ability to revise.

Source meaning → translated text
ADAPT THE CONTENT04

Speech Synthesis / Dubbing

Investigate TTS and dubbing workflows that connect translated dialogue with voice, pronunciation, and duration.

Translated dialogue → voice drafts
REVIEW & FINISH05

Timeline Editing & Quality Control

Develop video editing and QC tools for checking subtitle placement, audio timing, and how the pieces fit together.

Subtitle + audio + video → human review
REVIEW & FINISH06

Rendering & Output

Explore preparing the reviewed video, subtitle, and audio work for final rendering and output.

Reviewed material → final video

In development. This is not a list of released, completed, or production-ready features.

03 / PROPOSED WORKFLOW

A clear sequence.
Room to revisit.

Localization is a series of linked decisions. A change in wording may call for another pass at voice, timing, or the edit.

  1. 01

    Video Input

    Start with the video and its source language.

  2. 02

    Recognition

    Draft text from speech or visible subtitles.

  3. 03

    Translation

    Adapt the words to the target language.

  4. 04

    Voice / Timing

    Shape voice and align subtitle and audio timing.

  5. 05

    Human Review

    Check meaning, pronunciation, pacing, and fit.

  6. 06

    Output

    Prepare reviewed material for rendering.

Review is part of the process. Editors may return to earlier stages to correct text, refine a voice draft, or adjust timing.

Conceptual sequence only. It does not demonstrate an implemented end-to-end pipeline or a fully automated process.

04 / WHY XICHQUY

The challenge is
between the tasks.

Translating the words is one part of localizing a video. Getting the text, speech, and image to work together takes coordination—and a person who can judge the result.

01

Meaning needs context

A subtitle has to make sense in the scene. Recognition and translation drafts need careful review.

02

Timing changes the experience

Readable subtitles, natural speech, and the pace of the video need to fit the same timeline.

03

The editor connects the pieces

A desktop environment may help organize these interdependent tasks while leaving creative choices and final approval with people.

05 / DEVELOPMENT & STUDIO

Independent thinking.
Careful development.

XichQuy Studio is an independent software project exploring AI-assisted video processing and localization. The product direction is desktop-focused, with human review woven into recognition, adaptation, editing, and output.

The work is in progress. Specific capabilities, integration, and release availability remain subject to development and review.

In developmentDetailed feature statuses and release plans await Product Owner confirmation.

06 / CONTACT

Working on video,
language, or what’s next?

For startup inquiries, product conversations, or potential collaboration, get in touch by email.

founder@xichquy.xyz

Tell us what you’re working on and how you’d like to connect.