#Speech Synthesis

Qwen3-TTS — Open-source speech synthesis with a single pip install

A technical overview of Qwen3‑TTS from Alibaba’s Qwen team: one‑line pip install, 3‑second voice cloning, natural‑language voice design, and support for 10 languages including Japanese. Apache 2.0 licensed.

PersonaPlex: NVIDIA’s Real-Time Full‑Duplex Voice Conversational Model

Overview of PersonaPlex‑7B‑v1 released by NVIDIA in January 2026. A Moshi‑based voice dialog model that enables full‑duplex conversation and persona control.

KugelAudio — Open‑Source 7B‑Parameter TTS (ComfyUI‑Compatible)

Text‑to‑Speech covering 24 European languages with voice cloning. An open‑source model that outperformed ElevenLabs in the authors’ A/B tests.

Building a Talkable AI Environment (3): We're Finally Talking

The Web Speech API + Gemini + VOICEVOX setup is complete — an AI character you can actually have a voice conversation with. Key implementation notes and impressions.

Pocket TTS — Lightweight Text-to-Speech on CPU

Open-source TTS with 100M parameters that runs faster than real time on CPU. Supports voice cloning.

Building a Voice-Chat AI (1): Voice API Survey

Aiming for a characterful AI with an avatar and voice chat, I started by comparing voice APIs.

Trying to Have a Voice Conversation with AI

Planning a Japanese voice chat system built on the voice-chat project, using Gemini 2.0 Flash for LLM and VOICEVOX for TTS.