Skip to content

#语音

0 today

Jun 8Monday

AI HOT (Curated Pool)

VoxCPM2 technical report released

OpenBMB released the VoxCPM2 technical report, covering a 2B-parameter speech generation model trained on more than 2 million hours of multilingual speech data, with support for 30 languages and 9 Chinese dialects.

Why it matters: ModelBest open-sourced VoxCPM2, a 2-billion-parameter model under Apache 2.0, trained on over 2 million hours of data covering 30 languages and 9 Chinese dialects, with voice design, cloning and continuation all released.

May 12Tuesday

Latent Space

Thinking Machines' Native Interaction Models: TML-Interaction-Small 276B-A12B Advances Realtime Voice

Thinking Machines released TML-Interaction-Small, a 276B-parameter MoE model with 12B active parameters, and the post says it advances realtime voice through 200ms time-aligned microturns, encoder-free early fusion for audio and images under 200ms, and benchmark wins over GPT-Realtime-2 and Gemini 3.1-Flash.

Why it matters: Thinking Machines released TML-Interaction-Small, a 276B-parameter MoE with 12B active, building realtime voice interaction into the model instead of bolting on separate speech recognition and synthesis modules.

Apr 30Thursday

Google DeepMind

Google DeepMind announces AI co-clinician medical research program

Google DeepMind announced an AI co-clinician research program, exploring how AI agents can assist patient care under a doctor's clinical supervision. In a blinded evaluation of 98 real primary care queries, the system made no critical errors in 97 cases, and doctors preferred its answers over mainstream evidence synthesis tools. On 140 consultation skills, it matched or beat primary care physicians on 68, but expert physicians were still better overall at spotting red flags and key physical exams.

Why it matters: Google DeepMind details its AI co-clinician research program: in a blinded review of 98 real primary care queries, 97 had no critical errors, and doctors preferred its answers over mainstream evidence synthesis tools.

Apr 28Tuesday

QbitAI · WeChat

ModelBest Releases MiniCPM-o 4.5 Technical Report for Consumer-GPU Deployment

ModelBest, OpenBMB, Tsinghua THUNLP and THUMAI released the MiniCPM-o 4.5 technical report, covering a roughly 9B-parameter model. It supports video, audio and text streams; a 12GB RTX 5070 runs full-duplex mode at RTF 0.4. The key mechanism is Omni-Flow: a unified timeline with time-division multiplexing, without external VAD.

Why it matters: ModelBest with Tsinghua and others published the MiniCPM-o 4.5 technical report, a roughly 9B-parameter model using Omni-Flow to time-share audio, video and text on one timeline, running full-duplex on a 12GB consumer GPU.

Mar 21, 2025Friday

OpenAI News

Early methods for studying affective use and emotional well-being on ChatGPT

OpenAI and MIT Media Lab studied affective use on ChatGPT with two tracks: nearly 40 million interactions in an observational analysis and a 4-week RCT with nearly 1,000 participants. The post says emotional engagement is rare overall and concentrated in a small subset of heavy Advanced Voice Mode users; the provided body does not fully disclose all quantitative well-being results. Watch subgroup effects, not platform averages.

Why it matters: OpenAI and MIT paired observational analysis of nearly 40 million conversations with a four-week randomized trial of almost 1,000 people to study ChatGPT's emotional use and mental health.

Aug 8, 2024Thursday

OpenAI News

GPT-4o System Card

OpenAI published the GPT-4o System Card on August 8, 2024, reporting 3 of 4 Preparedness categories as low risk and persuasion as borderline medium. The post says GPT-4o accepts text, audio, image, and video inputs, responds to audio in as little as 232 ms with a 320 ms average, and is 50% cheaper than GPT-4 Turbo in the API. The key issue for practitioners is voice safety: the card names unauthorized voice generation, speaker identification, and sensitive trait attribution, and says only models with post-mitigation scores at medium or below can be deployed.

Why it matters: OpenAI's official system card gives the measured voice latency and names the audio safety risks, so teams can judge the multimodal limits from primary data.