Google has rolled out 66 regional voices across seven language categories in the Gemini mobile app, aiming to reproduce authentic local accents, pacing and clarity rather than exaggerated slang. The voices apply to both Gemini Live conversations and text-to-speech playback, and users can switch them in settings or mid-conversation.
TTS
文本转语音
Technology that synthesizes text into natural speech, here used for regional accent playback.
Curated Intelligence
DeepSeek has officially opened its full application API suite, splitting web search, deep-thinking search, file upload, link reading, and for the first time speech recognition and synthesis into independently callable, separately billed endpoints. The company says developers can replicate the complete DeepSeek App 1:1 and has open-sourced a lightweight chat frontend demo. Unlike the October Search/Fetch APIs that required manual tool orchestration, the new endpoints let the model autonomously decide when and what to search.
DeepSeek has exposed the full capability stack behind its consumer app through its API, letting developers enable web search, file and PDF parsing, link reading, safety filtering and voice with a few parameters, or call standalone OCR, ASR and TTS endpoints. An open-source frontend demo with conversation-history import support means developers can closely recreate the entire DeepSeek App.
Underdog released Woof, a text-to-speech model just 31.7MB in size, demoed through a browser-playable game that runs entirely on-device as a jab at cloud-based models. The startup also teased a 27-billion-parameter model that runs on laptops and a waitlisted locally hosted app.
The Gradium team released Phonon on Hugging Face, a small open-source text-to-speech model that runs entirely on-device with no server or network dependency, keeping user input local. The team says it leads Hugging Face's Open TTS Leaderboard and has opened an online demo for testing.
Developer Joey showcased a fully offline home voice assistant prototype using DeepSeek V4.1 Flash for reasoning and Ming-3.0 models for ASR and TTS. Running on NVIDIA DGX Sparks and a Mac mini, the setup achieves low-latency interaction with zero cloud dependency. The code repository is not yet public, remaining in a personal demo stage.
Voice Arena introduced the Turing TTS benchmark to decouple human-likeness from user preference in voice AI evaluation. Results show that even the top-performing model, Gemini 3.8 Flash TTS, fooled listeners only ~10% of the time, indicating a significant gap remains between current AI voices and real human speech.
Fish Audio released Drama 3, which ranks as the #1 open-weights model on Artificial Analysis Speech Arenas. It achieved the top score in Pronunciation Robustness (94.6%) among all models and offers a competitive price of $15 per million characters.
Following the release of Anthropic's Opus 5.5, AI agents can now autonomously perform complex video editing tasks with significant efficiency gains. The model achieves 'code-based editing' by generating HTML/CSS/JS, drastically reducing reliance on external skills and specialized editors, signaling a shift towards automation in video production.
Ollama has officially added text-to-speech (TTS) support to its Mac app, featuring the Gradium Phonon model. Leveraging Apple's MLX framework for local execution on Apple Silicon, it achieves up to 35% faster generation than previous implementations while supporting real-time streaming and multi-language accents.