Search AI Products and News

Nari Labs, a two-person startup, has released Dia, a 1.6 billion parameter text-to-speech (TTS) model designed to generate natural conversations directly from text prompts. Co-founder Toby Kim claims Dia surpasses proprietary offerings from competitors like ElevenLabs, as well as Google's NotebookLM AI podcast generation capabilities, and potentially even OpenAI's recently released gpt-4o-mini.

ByteDance Research has announced the open-sourcing of ChatTS-14B, a 14-billion parameter large language model (LLM) specifically designed for understanding and reasoning with time series data. Released under the Apache2.0 license, ChatTS-14B's open-source release has garnered significant attention within the AI community, marking a substantial advancement in the intersection of time series analysis and generative AI. ChatTS-14B: An Intelligent Conversational Engine for Time Series. ChatTS-14B is based on Qwen2.5-1...

Beijing—ByteDance recently released its latest text-to-speech (TTS) model, MegaTTS3, on the Hugging Face open-source AI community. This release has quickly garnered attention from AI researchers and developers worldwide due to its breakthroughs in lightweight design and multilingual support. Based on community feedback and official information, MegaTTS3 is hailed as a significant advancement in speech synthesis. MegaTTS3's core highlights are...

Following previous attention in the speech AI field, OpenAI continues its exploration, releasing three new self-developed speech models: gpt-4o-transcribe, gpt-4o-mini-transcribe, and gpt-4o-mini-tts. The most notable is gpt-4o-transcribe. These new models are currently...

On March 19th, an open-source text-to-speech (TTS) model called Orpheus TTS was officially launched. This model has quickly gained attention for its human-like emotional expression, natural and fluent voice quality, and ultra-low latency real-time output stream. Orpheus TTS reportedly excels in real-time conversational scenarios and promises to bring new breakthroughs to intelligent voice interaction. Orpheus TTS focuses on low latency and high emotional expression, with core features including: - **Ultra-Low Latency**: Default latency approximately 2

Recently, a study conducted by the non-profit organization Epoch AI revealed the energy consumption of OpenAI's chatbot platform ChatGPT, showing that its energy use is significantly lower than earlier estimates. According to some reports, ChatGPT consumes about 3 watt-hours of power to answer a question; however, Epoch AI's research suggests that this figure has been overstated. The study indicates that when using OpenAI's latest default model GPT-4o, the average energy consumption per query is only...

On January 20, 2025, Doubao App officially released its latest 'end-to-end' voice large model, with significant updates to its real-time voice call functionality. This development marks another leap for Doubao in the field of voice interaction, surpassing the previous ASR (Automatic Speech Recognition), LLM (Large Language Model), and TTS (Text-to-Speech) cascading solutions by integrating voice recognition, understanding, and generation into a single model. After testing by 'Intelligent Emergence,' the standout feature of the new Doubao version is its human-like capabilities.

A recent study reveals that readers struggle to distinguish between poems created by human poets and those generated by artificial intelligence. Surprisingly, many participants rated the AI-generated poems even higher than those by renowned poets. This research was conducted by Brian Porter, a postdoctoral researcher at the University of Pittsburgh, and his team, with results published this week in Nature Scientific Reports. Image source note: The image was generated by AI, selected by the Midjourney research team's licensing service.

Recently, Oute AI released a novel text-to-speech synthesis method called OuteTTS-0.1-350M. This method utilizes pure language modeling without the need for external adapters or complex architectures, offering a simplified TTS approach. OuteTTS-0.1-350M is based on the LLaMa architecture, using WavTokenizer to directly generate audio tokens, making the process more efficient. The model features zero-shot voice cloning capability, requiring only a few seconds of reference audio.

Geely Auto has recently achieved a significant breakthrough in the field of speech synthesis, with its self-developed HAM-TTS large model outperforming the industry benchmark VALL-E, attracting widespread attention in the industry. This AI large model, named "Xingrui," has achieved significant improvements in key indicators such as pronunciation accuracy, naturalness, and speaker similarity. The HAM-TTS model utilizes token-based zero-shot text-to-speech hierarchical acoustic modeling technology, greatly enhancing the user interaction experience in intelligent cockpits. Under the same conditions of 400 million parameters, HAM-TTS...