VoxCPM2
PulseAugur coverage of VoxCPM2 — every cluster mentioning VoxCPM2 across labs, papers, and developer communities, ranked by signal.
- 2026-09-15 product_launch OpenBMB released the open-source text-to-speech model VoxCPM2. source
3 day(s) with sentiment data
-
Open-source film studio built on ComfyUI and MiniMax H3 for PC use
A developer has created IV Studio, a free, open-source desktop application that leverages ComfyUI and MiniMax H3 to enable users to produce short films on their personal computers. The application automates various stag…
-
New TTS research questions decodability vs. controllability in speaker voice synthesis
A new research paper published on arXiv explores the nuances of speaker control in continuous-latent text-to-speech (TTS) systems. The study, titled "Decodability Is Not Controllability," demonstrates that high linear d…
-
Tyger model enables open-weights full-duplex voice agent turn-control
A new open-weights model named Tyger has been released, designed for full-duplex turn-control in voice agents. It operates by analyzing audio from both the user and the agent's playback to determine the appropriate resp…
-
OpenBMB releases 2B-parameter open-source TTS model, VoxCPM2
OpenBMB has released VoxCPM2, an open-source text-to-speech model with 2 billion parameters. This model is capable of generating speech in 30 different languages and was trained on 2 million hours of audio data. It is a…
-
New framework diagnoses TTS failures in complex multilingual text
Researchers have developed a new framework to evaluate the robustness of low-resource multilingual text-to-speech (TTS) systems when processing complex text inputs. This framework assesses content consistency, language …
-
WanSong model generates 5-minute songs with dual stems using diffusion
Researchers have introduced WanSong, a novel diffusion-based model designed for generating long-form, commercial-grade songs. This model directly produces high-fidelity, multilingual songs up to five minutes in length, …
-
New TTS system BlueMagpie-TTS targets Taiwanese Mandarin code-switching
Researchers have developed BlueMagpie-TTS, a novel text-to-speech system specifically tailored for Taiwanese Mandarin and code-switching speech. The system introduces PangolinTokenizer, a byte-level tokenizer optimized …
-
audio.cpp framework offers faster audio model inference
A new C++ inference framework called audio.cpp has been developed, built on top of ggml, to run various audio models including TTS, ASR, and voice conversion. The framework aims to consolidate multiple audio models into…
-
LoRA Fine-Tuning Boosts Low-Resource TTS Quality for Khmer
Researchers have developed a method to improve the quality of text-to-speech (TTS) for low-resource languages like Khmer and Korean. By fine-tuning the 2.4B-parameter VoxCPM2 model using a single Low-Rank Adaptation (Lo…
-
Rust RAG, Tokenizer-Free TTS, and Offline AI Survival Computer
This cluster highlights advancements in local and offline AI deployments. It features a guide on building high-performance Retrieval Augmented Generation (RAG) systems using Rust, emphasizing performance and control for…