$ articles --topic=voice-and-vision
Voice and Vision
14 AI articles about Voice and Vision.
Voice Chat with AgentsLearn how to start a realtime voice call with your Cursor agents, ask them about running work and diffs, and hear progress updates as they code. Voice chat works in the Agents Window, the IDE, on web, and iOS, and runs on Grok Voice.AI Coding Tools · via Cursor Changelog · 1d ago2 minA Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.Open Models · via Hugging Face · 2d ago1 minIntroducing Images 2.6Images 2.6 is a new release that speeds up image generation, adds GIF creation, and offers more precise editing. It also introduces new API controls that work across ChatGPT, Codex, and the API.Model Releases · via OpenAI News · 3d ago1 minCustom Voices With Qwen3-TTSLearn how to build custom TTS voices with Qwen3-TTS by blending voice embeddings from a designed voice and a real recording, and how to add emotional instructions like sad or whispering to a cloned voice by pairing a Base speaker embedding with the CustomVoice model.Open Models · via Armin Ronacher · 9d ago9 minOptimizing Streaming Speech Recognition on Arm® Edge Devices with ExecuTorchShows how to evaluate streaming speech recognition on an Arm edge device by measuring accuracy and latency together. It covers Nemotron 3.5 running on ExecuTorch with FP16 and INT8 precision, the effect of chunk size on word error rate, and how SME2 cuts processing time on a Google Pixel 11.Open Models · via PyTorch · 12d ago8 minSpeech models in OllamaOllama has added support for speech models, beginning with Phonon from Gradium. The post explains how it reads text aloud in five languages with dozens of voices, streams audio as it is generated, and runs over 100 times faster than real time on Apple Silicon.Open Models · via Ollama · 14d ago1 minVoxtral 3Voxtral 3 is Mistral's SDK for building voice agents. It covers real-time speech handling across more than 50 languages, transcription, expressive text-to-speech, and tool use within voice workflows.Agents · via Mistral · 18d ago1 minIntroducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flashExplains Cloudflare's new Clef-omni open-weight decision model, which accepts audio, video, image, and text input in one API call, plus a cheaper Clef-flash with a reduced 24k context window and a faster hosted Clef. Includes benchmark comparisons against Clef, Clef-flash, and Jev.Model Releases · via Cloudflare AI · 29d ago8 minCreate your own voice for Gemini 3.8 TTSLearn how to create a custom voice in Gemini 3.8 TTS, either by replicating your own voice or designing one from a text description. The article also covers directing delivery line by line with Gemini 3.8 Flash TTS.Model Releases · via Philipp Schmid · 1mo ago1 minBuild real-time voice applications with Gemini 3.8 Live and 3.5 TranscribeA developer-focused overview of building real-time voice applications with Gemini 3.8 Live, its Extended Thinking variant, and 3.5 Transcribe. It covers how these latest audio models fit into voice app development.Model Releases · via Google Developer Tools · 1mo ago1 minIntroducing agentic video understanding with GeminiAgents · via Google DeepMind Blog · 2mo ago1 minGemini Omni 1.1 Flash lets you build with more controlGemini Omni 1.1 Flash is a model release for developers that adds new creative controls and generative video capabilities. The post covers what the model can do and how these controls let builders shape their output. It is aimed at developers working with generative video.Model Releases · via Google Developer Tools · 2mo ago1 min