alexturkey/voxcpm2-turkce-ses-tasarimi

One-step Turkish text-to-speech trained with a drifting objective (Kyutai learned-temperature recipe)

Ahenk: açık Türkçe metinden sese. Open Turkish text-to-speech: VoxCPM2 LoRA (Ahenk), 8.6M on-device model (Ahenk Cep), trnorm text normaliser, TR-Zor benchmark

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

VoiceStudio is a local-first, free text-to-speech studio for multi-languages. Create polished voiceovers with named neural voices, style presets, pitch/rate/volume controls, browser preview, local history, and MP3/WAV/AAC export—no API key required.

Tiny, fast and accurate Turkish text-to-speech. 8.6M parameters, 0.92% WER on Freya-TR-Eval, first audio in ~4 ms and 1,300× real time on one GPU. Streams audio, batches many callers on one GPU, and runs offline on a GPU or CPU.

Desktop app with Compose Multiplatform to use Qwen3-TTS with an UI.

Portable Windows build of VoxCPM2 — multilingual TTS (30 languages incl. Russian), Voice Design, Voice Cloning, and end-to-end LoRA fine-tuning (video/audio → dataset → training). One-click install.

A TTS that fits in your CPU (and pocket)

On-device TTS model by Neuphonic