# AI use cases for Cit Voice Studio (Cuongyd196/cit-voice-studio)

Repo: [Cuongyd196/cit-voice-studio](https://github.com/Cuongyd196/cit-voice-studio) | Use cases: 3 | Page: https://dedupedai.com/use-cases/cuongyd196-cit-voice-studio/

CIT Voice Studio is a desktop app that turns Vietnamese text into speech on your own computer, offline after install, and can also be driven through a local API.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Generate separate narration audio files from one text file: https://dedupedai.com/use-cases/cuongyd196-cit-voice-studio/batch-narration-from-text-file/
- Dub a video in Vietnamese from its subtitle file: https://dedupedai.com/use-cases/cuongyd196-cit-voice-studio/dub-video-from-srt-subtitles/
- Let an AI agent generate Vietnamese WAV files through the local API: https://dedupedai.com/use-cases/cuongyd196-cit-voice-studio/agent-calls-local-tts-api/

## How to generate separate narration audio files from one text file with Cit Voice Studio

Repo: [Cuongyd196/cit-voice-studio](https://github.com/Cuongyd196/cit-voice-studio) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

Split a long Vietnamese script into one audio file per [P] section using the Batch tab, with a zip download.

**Who it is for:** A content creator, teacher, or course author who has a long Vietnamese script in chapters or parts and needs one audio file per part on a personal computer.

**The problem:** Recording or generating a long script in one go is slow, and a single failure forces a full redo. Splitting by hand is tedious.

**The outcome:** Each section of the script becomes its own WAV or MP3 file, all downloadable individually or as one .zip, with no internet connection needed after install.

### Steps

1. Download the installer for your system from the Releases page at https://github.com/Cuongyd196/cit-voice-studio/releases/latest (or the Google Drive link in the README if GitHub is slow).
2. Install and open CIT Voice Studio. On Linux, run `sudo apt install ./CIT-Voice-Studio-v1.0.3-amd64.deb` and then open CIT Voice Studio from the app menu.
3. Open the Tạo hàng loạt tab, then paste the script or upload a TXT file. Put a marker such as [P1] and [P2] at the start of each line that should become its own file.
4. Choose a voice and speed, then start generation. Keep the app open until it finishes.
5. Download each file one by one, or download all of them in one .zip file.

### Prompt to paste into your agent

```text
Using the CIT Voice Studio app already installed on this computer, take the script in <script-file-path>, insert [P1], [P2] and so on at the start of each section, and run it through the Tạo hàng loạt tab. Expected output: one WAV or MP3 file per section plus a .zip of all files. Verify that the number of output files equals the number of [P] markers in the script.
```

### Caveat

The app keeps working only while it is open, and the README says the Linux and macOS builds show a Terminal window or browser tab that must stay open during use.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/cuongyd196-cit-voice-studio/batch-narration-from-text-file/

## How to dub a video in Vietnamese from its subtitle file with Cit Voice Studio

Repo: [Cuongyd196/cit-voice-studio](https://github.com/Cuongyd196/cit-voice-studio) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Read each subtitle line at its exact timestamp and export one audio track that fits the video timing.

**Who it is for:** A video editor or creator who already has an .srt or .vtt subtitle file for a video and wants a Vietnamese voice track to add in CapCut, Premiere, or a similar editor.

**The problem:** Recording voice-over that matches each subtitle timing by hand is slow, and misaligned narration is hard to fix in the editor.

**The outcome:** A single WAV or MP3 audio file whose lines sit at the same timestamps as the subtitles, plus an adjusted .srt file if any lines had to shift.

### Steps

1. Install CIT Voice Studio from the Releases page at https://github.com/Cuongyd196/cit-voice-studio/releases/latest and open it.
2. Open the Đọc file tab and drop your .srt or .vtt file into it. Check the list of lines and timestamps that appears.
3. Choose a voice and a reading speed, then click Lồng tiếng.
4. Listen to the result, then download the WAV or MP3 file. If the app shows a subtitle file with shifted timestamps, download that too.
5. Import the audio into your video editor and place it on the timeline, then use the adjusted .srt for the on-screen text if it was shifted.

### Prompt to paste into your agent

```text
Using the CIT Voice Studio app on this computer, dub the subtitle file <path-to-srt-file> into Vietnamese through the Lồng tiếng feature. Expected output: one audio file whose total length matches the video, plus an adjusted .srt if lines were shifted. Verify that the audio length matches the video duration and that no sentence is cut off.
```

### Caveat

The README says sentences that run long are read faster, up to 1.5 times, and may push later sentences back, so very dense subtitles may need a lower speed or shorter wording.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/cuongyd196-cit-voice-studio/dub-video-from-srt-subtitles/

## How to let an AI agent generate Vietnamese WAV files through the local API with Cit Voice Studio

Repo: [Cuongyd196/cit-voice-studio](https://github.com/Cuongyd196/cit-voice-studio) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README

Point a script or coding agent at the app's local API on port 8001 to create speech files automatically.

**Who it is for:** A developer or automation builder who wants a coding agent or script to create Vietnamese voice files as part of a larger workflow, such as a content pipeline.

**The problem:** Each speech file has to be made by hand in the app, which does not scale when an agent or script needs many files.

**The outcome:** Speech files are generated by the agent or script through the local API, saved to disk, and checked against the expected output.

### Steps

1. Install CIT Voice Studio and keep the app open, since the README says the local API runs only while the app is open.
2. Open http://127.0.0.1:8001/health in a browser to confirm the server is running.
3. Open http://127.0.0.1:8001/docs to test the /api/tts/generate endpoint and see the request format.
4. Open http://127.0.0.1:8001/cit-voice-studio.md and load it into Cursor as integration context.
5. Run the agent or the Python example from the README, which sends a POST request to /api/tts/generate and saves the returned audio.

### Prompt to paste into your agent

```text
Using the CIT Voice Studio API running at http://127.0.0.1:8001, send POST requests to /api/tts/generate with the text from <input-text-file> and voice_id "Minh Đức", then save each response as a WAV file in <output-folder>. Expected output: one WAV file for each input text. Verify that each saved file opens and has a non-zero size.
```

### Caveat

The API works only on the same computer by default, and the README warns that LAN access sends the API key over unencrypted HTTP, so keep it local unless you add HTTPS.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/cuongyd196-cit-voice-studio/agent-calls-local-tts-api/