A C++ speech toolkit on ggml for text-to-speech, speech recognition and voice activity detection, running on Metal, Vulkan or CPU with an OpenAI-compatible server.
alexturkey/voxcpm2-turkce-ses-tasarimi
Turkish voice design tool built on VoxCPM2 that runs on a 4 GB NVIDIA GPU, with a local web UI and bundled synthetic voices.
- Stars
- 387
- Forks
- 49
- Open issues
- 4
- Last commit
- yesterday
What is it?
This project generates speech with VoxCPM2 in Turkish and seven other languages. You describe a voice in English, the model creates several variants, and you choose one to read any Turkish text. Designed voices are reused through a reference recording and a fixed seed, so the voice stays consistent from sentence to sentence.
The engine is a patched audio.cpp build that fits the model into about 2.8 GB of VRAM, so it runs on cards such as the GTX 1050 Ti. The repository includes a one-command Windows installer, a macOS Apple Silicon path with Metal, a Linux Docker option, a small local web UI, and fourteen ready-made voices covering Turkish and native narrators in English, French, German, Spanish, Russian, Chinese and Japanese.
A voice cloning tab is included for your own voice or a voice whose owner has given explicit permission, and the UI requires that confirmation before running.
Key features
- 01Designs new voices from an English text description and generates several variants to compare.
- 02Reads Turkish text sentence by sentence with a consistent voice from a reference recording and seed.
- 03Runs on NVIDIA GPUs with 4 GB VRAM using a patched audio.cpp engine.
- 04Provides a local web UI and command-line tools for designing and reading.
- 05Includes 14 bundled synthetic voices across 8 languages.
- 06Supports macOS Apple Silicon via Metal and Linux via Docker or build scripts.
Use cases
- Producing Turkish narration for documentaries, videos or audiobooks on a modest local GPU.
- Dubbing videos with a designed voice through the DubWorld program that uses this engine.
- Prototyping character or narrator voices from text descriptions before recording.
- Generating multilingual narration samples in English, French, German, Spanish, Russian, Chinese and Japanese.
Quick start
- 1
Download and extract the code zip from the GitHub page
- 2
Run the installer in PowerShell from the extracted folder (sets up to C:\vox)
powershell -NoProfile -ExecutionPolicy Bypass -File scripts\kur.ps1 -Kok C:\vox - 3
Double-click baslat.bat to start the local web UI at http://127.0.0.1:8765/
Things to know
- Windows install needs an NVIDIA GPU with at least 4 GB VRAM and driver 570 or newer.
- AMD and Intel GPU support uses an experimental Vulkan build.
- Linux support is experimental and needs an NVIDIA GPU with CUDA.
- The installer downloads about 3.7 GB.
In collections
Topics
FAQ
- What is voxcpm2-turkce-ses-tasarimi?
- Turkish voice design tool built on VoxCPM2 that runs on a 4 GB NVIDIA GPU, with a local web UI and bundled synthetic voices. This project generates speech with VoxCPM2 in Turkish and seven other languages. You describe a voice in English, the model creates several variants, and you choose one to read any Turkish text. Designed voices are reused through a reference recording and a fixed seed, so the voice stays consistent from sentence to sentence.
- Is voxcpm2-turkce-ses-tasarimi free to use? What license does it have?
- voxcpm2-turkce-ses-tasarimi is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is voxcpm2-turkce-ses-tasarimi still maintained?
- Actively maintained. The last commit to voxcpm2-turkce-ses-tasarimi was on Nov 5, 2026.
- What can I use voxcpm2-turkce-ses-tasarimi for?
- Producing Turkish narration for documentaries, videos or audiobooks on a modest local GPU. Dubbing videos with a designed voice through the DubWorld program that uses this engine. Prototyping character or narrator voices from text descriptions before recording. Generating multilingual narration samples in English, French, German, Spanish, Russian, Chinese and Japanese.
- How do I install voxcpm2-turkce-ses-tasarimi?
- Download and extract the code zip from the GitHub page Run the installer in PowerShell from the extracted folder (sets up to C:\vox): powershell -NoProfile -ExecutionPolicy Bypass -File scripts\kur.ps1 -Kok C:\vox Double-click baslat.bat to start the local web UI at http://127.0.0.1:8765/
- Where can I get voxcpm2-turkce-ses-tasarimi?
- The source code and installation instructions are on GitHub: https://github.com/alexturkey/voxcpm2-turkce-ses-tasarimi
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source voice AI family from Microsoft, with long-form speech recognition (ASR), multi-speaker text-to-speech (TTS), and real-time streaming TTS models.
Open-source text-to-speech system with voice cloning, natural-language emotion control and multi-speaker generation, built on LLM-style models.
A zero-shot text-to-speech system that clones a voice from one reference audio clip, with emotion, speed and pronunciation control.
Python inference library for Kokoro-82M, an open-weight text-to-speech model with 82 million parameters.
A VITS2-based text-to-speech project that adds multilingual BERT to improve prosody and pronunciation in synthesized speech.