TechFeb 3, 2026updatedKugelAudio — 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.ComfyUITTSSpeech SynthesisAI
TechJan 19, 2026Building a Talkable AI Environment (3): We're Finally TalkingThe Web Speech API + Gemini + VOICEVOX setup is complete — an AI character you can actually have a voice conversation with. Key implementation notes and impressions.AISpeech RecognitionSpeech SynthesisVOICEVOXGeminiWeb Speech APISwitchBotExperiment
TechJan 15, 2026updatedPocket TTS — Lightweight Text-to-Speech on CPUOpen-source TTS with 100M parameters that runs faster than real time on CPU. Supports voice cloning.AISpeech SynthesisTTSOpen Source
TechJan 10, 2026Building a Voice-Chat AI (1): Voice API SurveyAiming for a characterful AI with an avatar and voice chat, I started by comparing voice APIs.AISpeech SynthesisSpeech RecognitionTTSSTTGeminiOpenAIChatGPTVOICEVOXGoogle Cloud
TechDec 30, 2025Trying to Have a Voice Conversation with AIPlanning a Japanese voice chat system built on the voice-chat project, using Gemini 2.0 Flash for LLM and VOICEVOX for TTS.AIGeminiVOICEVOXSpeech RecognitionSpeech SynthesisExperiment
