NVIDIA showcased 'MonsterHouse', an interactive Halloween projection built on the Nemotron open model stack. The application integrates Nemotron ASR, Magpie TTS, and Audio2Face-3D to create a real-time voice agent with emotional feedback capabilities. This case serves primarily as a technical demonstration of multimodal component integration in specific scenarios.
Zero-shot TTS
零样本语音合成
Generating a specific speaker's voice without fine-tuning, using only a short reference audio clip
Curated Intelligence
Ant Ling has open-sourced the Ming-3.0 voice series, comprising five models for TTS, ASR, and audio understanding. The release introduces a 'Director Mode' for fine-grained control over speech emotion and rhythm, alongside enhanced structured understanding of long audio. These capabilities are already deployed in Ant Group's internal services like Alipay.
Google has released Gemini 3.8 Flash TTS and Flash-Lite TTS, its most expressive audio generation models to date. These models allow users to create or replicate custom character voices via natural language prompts and direct scene dialogue line-by-line to control pacing and emotion, targeting use cases like audiobooks, podcasts, and real-time voice agents.
Alibaba's Qwen team released two new models: Qwen3-TTS-VD-Flash for voice design and Qwen3-TTS-VC-Flash for voice cloning. The former allows fine-grained control over timbre, emotion, and persona via natural language instructions, while the latter supports 3-second multi-language voice cloning. Benchmarks indicate superior performance over GPT-4o-mini-tts and ElevenLabs in InstructTTS-Eval and multilingual WER metrics.
OpenAI shared preliminary results for Voice Engine, a model that generates highly realistic custom speech using just text and a 15-second audio sample. While the technology already powers preset voices in ChatGPT, OpenAI is delaying broader release due to misuse concerns like deepfakes. The disclosure highlights significant breakthroughs in emotional expression and voice cloning with small models.