Coder Legion - Recent posts tagged whisper

Whisper Transcriber - v0.5 Usage Note - Run Whisper Models Locally | Desktop AI

Mon, 25 Aug 2025 00:26:18 +0000

Overview

Whisper Transcriber transcribes audio into text using the amazing Whisper model from OpenAI. It supports both official OpenAI API and locally deployed Whisper models.

This simple tool is published for free for those who need to easily transcribe complex audio with OpenAI's Whisper models, all under your full control.

Usage

You can now use Whisper Transcriber tool either with official OpenAI API, or with locally deployed Whisper models.

With OpenAI API

Register and obtain an OpenAI developer key from OpenAI (See video guide)
Open Transcriber
Type your key (If you wish this to be filled automatically, setup an environment variable OPENAI_API_KEY)
Select target language: See Dev Log for a full list of supported languages.
Start recording or load existing audio files to transcribe!

With Locally Deployed Models

Pick "Local" from dropdown to use locally deployed models.
Pick a suitable model. Larger models run slower but are more accurate. Smaller models generally suffice.
Pick a language or use "Auto" for automatic language detection.
When picking from available models, it will automatically download the models to the executable folder.

If you want to speed up the process, you can download commonly used models from the download section of the website and place those model files yourself. See video guide for detail.

Supported Languages

Catalan
Chinese
Czech
Dutch
English
French
German
Indonesian
Italian
Japanese
Korean
Polish
Portuguese
Russian
Spanish
Swedish
Turkish
Ukrainian

Resources

Download: https://methodox.itch.io/transcriber
More from Methodox: https://methodox.itch.io/
Audio Transcription Guide: https://platform.openai.com/docs/api-reference/audio
Official API: https://platform.openai.com/docs/api-reference/audio
Whisper Model: https://github.com/openai/whisper

If you enjoyed this AI tool, please also consider our Chat Gateway service - which enables you to quickly add an AI-enabled chat bot to your personal website! Visit official website for more!

Whisper Transcriber

Sat, 23 Aug 2025 21:41:19 +0000

Annoucement

Hey everyone! We are glad to share this transcriber tool that we've been developing and using. We find it very helpful when trying to take long notes in a narrative style. Whisper Transcriber is a free utility program by Methodox that transcribes audio into text using the amazing Whisper model from OpenAI.

This simple tool is for those who need to easily transcribe complex audio with OpenAI's Whisper models. It current supports the official OpenAI API (so no sophisticated setup is needed) - in the future, we plan to support locally deployed Whisper models (which requires a dedicated GPU) as well.

We wish you find it helpful!

Usage

Register and obtain an OpenAI developer key from OpenAI (See video guide)
Open Transcriber
Type your key (If you wish this to be filled automatically, setup an environment variable OPENAI_API_KEY)
Select target language: Currently supports English and Chinese
Start recording or load existing audio files to transcribe!

This software is cross-platform - Linux and Mac version is available on request.

Changelog

v0.1: First build.
v0.2: Component update per framework change; Make OpenAI key configurable during runtime.
v0.3: Allow picking save path.
v0.4: Improve GUI; Show recording durations; Update executable name.
v.04.1: Support automatic segmentation; Improve HTTP request stability.

Disclaimer

THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

References

Itch Store Link: https://methodox.itch.io/transcriber
Audio Transcription Guide: OpenAI Guide
Official API: API Reference
Whisper Model: Github

Video Guide: Transcriber - Use OpenAI API to Turn Audio Into Text | Whisper Audio Transcription | Utility

If you enjoyed this AI tool, please also consider our Chat Gateway service - which enables you to quickly add an AI-enabled chat bot to your personal website! Visit official website for more!

Voice-Pro: Your Voice, Reimagined Across Languages

Fri, 14 Mar 2025 20:17:12 +0000

Imagine a world where your voice can speak any language fluently, without ever stepping into a recording booth. Meet Voice-Pro—a groundbreaking tool that harnesses advanced voice cloning technology to create seamless multilingual dubbing. Whether you’re a filmmaker breaking into global markets, a business reaching diverse audiences, or a creator pushing the boundaries of storytelling, Voice-Pro transforms how you connect through sound.

What Makes Voice-Pro Stand Out?

Lifelike Voice Cloning: Captures the essence of your voice—tone, emotion, and all—for authentic results.
Multilingual Magic: Effortlessly dubs your content into multiple languages with natural fluency.
Simple Yet Powerful: Designed for ease of use, delivering professional-grade output without the complexity.
Versatile Applications: From entertainment to education, it’s built to adapt to your needs.

Curious about the tech behind it? Check out the GitHub repository for a detailed README, including setup instructions. Voice-Pro runs on Python and can be deployed locally with just a few steps.

See Voice-Pro in Action

Want to witness the power of voice cloning and multilingual dubbing? These YouTube videos showcase what Voice-Pro can do:

Voice-Pro Demo 1: A peek into the core voice cloning tech and its stunning realism.
Voice-Pro Demo 2: Real-world examples of multilingual dubbing that redefine global content creation.

Why Voice-Pro Matters

In a world where communication knows no borders, Voice-Pro empowers you to amplify your voice like never before. Stay tuned for updates as we continue to refine this game-changing technology—because your story deserves to be heard, everywhere.