AI Voice

Turn text or a few seconds of reference audio into natural speech—AI voice makes audiobooks, courses, and character dubbing possible without a studio or voice actor.

AI voice rests on TTS and voice cloning. Open models like Qwen3-TTS, GLM-TTS, and MOSS-TTS-Nano already clone a voice in three seconds and control emotion. Before producing audio, check multilingual support, CPU-only running, and whether cloning needs consent.

Alibaba Qwen Launches Qwen-Audio-3.1: Five Voice Models at Once, ASR Prices Cut 95%

On September 23, 2026, Alibaba's Qwen team officially launched the Qwen-Audio-3.1 family of voice models: five new models released in one go, covering...

Admin 9/23/2026

216

MOSS-TTS-Nano Analysis: 0.1B open-source multilingual TTS, the CPU can also generate voice in real time

1. Abstract MOSS-TTS-Nano is a comparative version of OpenMOSS and MOSI. The open-source multilingual speech generation model released by AI is positi...

Admin 4/14/2026

748

Qwen3-TTS open source release: 12Hz high-compression tokenizer + 3 seconds of tone clone How to play

1. Abstract Qwen3-TTS is a family of open-source text-to-speech (TTS) models from the Qwen team, including VoiceDesign (to generate new voices from te...

Admin 1/23/2026

232

GLM-TTS is fully open source: 3-second voice cloning with emotionally controllable industrial-grade speech synthesis

1. Abstract GLM-TTS is an open-source TTS system for industrial-grade speech generation, supporting timbre cloning of voice samples in just 3 seconds ...

Admin 12/11/2025

292