Skip to content
Date and source

Dates follow the news timeline in Beijing time and include both endpoints.

Oct 6Tue
  1. Hedra 官方博客60

    Hedra Launches Developer API: One Key to Access 110+ Generative Models

    Hedra launches its Developer API, allowing access to 110+ generative models with a single API key and prepaid USD wallet, covering video, image, audio, and text, including Veo 3.1, Kling V3, Seedance 2.5, MiniMax H3, Nano Banana Pro, ElevenLabs V3, and more.

    Why it matters: Hedra consolidates 110+ video, image, audio, and text models into a single API and prepaid wallet, enabling developers to evaluate the integration costs of multi-model pipelines.

  2. yanhuo-easy-use · ComfyUI创作项目发布12

    yanhuo-easy-use Fixes False Flagged Issue in 1.3.0 and Adds Pre-Publish Self-Check Script

    yanhuo-easy-use fixes the issue where version 1.3.0 was flagged: a YARA rule mistakenly identified the JS Function binding syntax in web/js as a Python socket binding, so Reflect.apply was used instead to eliminate the literal string. A pre-publish self-check script tools/check_publish_hygiene.py has also been added.

  3. HeyGen Updates55

    HeyGen Voices Integrates ElevenLabs v4 Text-to-Speech Model

    HeyGen Voices now supports ElevenLabs v4, which the company calls ElevenLabs' most expressive text-to-speech model to date. v4 delivers script readings closer to voice actor delivery, maintaining rhythm and tone consistently from start to finish on long scripts, and preserving the same voice timbre when regenerating the same line. To use it, select a voice in Voices and choose ElevenLabs v4.

  4. mlx-audio · 开源创作项目发布10

    mlx-audio v0.5.8 released: fixes Voxtral streaming and TTS issues and speeds up Qwen3 timestamp fix

    mlx-audio released v0.5.8, fixing Voxtral streaming packet boundary drift, Voxtral TTS first-frame decoding and MOSS convolution layout loading issues, while preserving breeze's bf16 prompt embedding precision. This version also speeds up the Qwen3 timestamp fix and adds a real-time transcription capability interface, which was then reverted.

  5. huobao-drama · 开源创作项目发布17

    huobao-drama v4.0.8 released: quick configuration supports domestic/international node selection

    huobao-drama v4.0.8's quick configuration adds domestic/international node selection, defaulting to follow the interface language: Chinese corresponds to firemux.cn, other languages to firemux.com. The one-click recommended configuration and the Key acquisition link are generated according to the selected node.

Oct 5Mon
  1. Toonflow-app · 开源创作项目发布18

    Toonflow 2.0.4 released

    Toonflow 2.0.4 released, offering three installer downloads: Windows (64-bit), M-series Mac and Intel Mac. The M-series Mac installer has completed Developer ID signing and Apple notarization, though macOS may still prompt for confirmation on first open. See v2.0.3...v2.0.4 for the full changelog.

  2. ComeCut · 开源创作项目发布18

    ComeCut resource pack v1.0 released

    ComeCut released resource pack v1.0, containing three files: ffmpeg-win-x64.zip provides the FFmpeg calling library, models.zip provides the local models required by specific features, and onnxruntime-win-x64.zip provides the model inference environment.

  3. H3 Temporal Sampler · ComfyUI创作项目发布43

    ComfyUI H3 Temporal Sampler v1.5 released: renamed and adds Seam Lock multi-frame gradient freeze

    The ComfyUI creative project H3 Temporal Sampler released v1.5, renamed from its original name to H3 Temporal Sampler, and added the Seam Lock multi-frame gradient freeze feature. This version also updates default parameters: Smart Bounds off, Overlap set to 5, Blend using multiband, and Seam Lock Frames set to 2.

Oct 4Sun
  1. InvokeAI 官方发布62

    InvokeAI 7.0.0 alpha 1 released: all-new workbench, canvas engine, and video panel

    InvokeAI released 7.0.0 alpha 1, calling it its largest update ever, with about 320 PRs and 2,600 commits, requiring Python 3.12, and with the new interface as default.

    Why it matters: InvokeAI 7 integrates canvas, workflows, and video generation into a single workbench, and adds support for models such as MiniMax H3 and LTX-2.5, which can be used to judge whether to migrate an existing image generation workflow.

Oct 3Sat
  1. openscreen · 公开创作项目发布34

    OpenScreen 2.0 released: a polished demo on your first recording

    OpenScreen 2.0 is released, built around the idea that it "looks good without tweaking settings, and won't look bad even if you do," adding an editor and support for automatically planning zoom shots based on clicks. The new version halves the default cursor size, raises the 1080p60 export bitrate from 8 Mb/s in 1.x to 18.7 Mb/s, normalizes audio to -16 LUFS, and switches transcription to Silero VAD with re-alignment of each word's timing. This version remains completely free for personal and commercial use, with no paywall, and 1.x projects can be opened directly.

  2. openscreen · 公开创作项目发布10

    OpenScreen v2.0.0-rc.15 released

    OpenScreen released v2.0.0-rc.15; changes since v2.0.0-rc.14 include: the preview feature no longer decodes a substitute camera when a clip has no camera, and records the free-running decode budget; on the testing side, a passing record of the macOS computer-use end-to-end test was added, and it was verified that the substitute camera never moves.

  3. MoneyPrinterTurbo · 开源创作项目发布50

    MoneyPrinterTurbo v1.3.8 released: adds VoxCPM voice cloning and a local video project CLI

    MoneyPrinterTurbo v1.3.8 adds VoxCPM reference-audio voice cloning and tone/emotion transfer, and adds the MuAPI video asset source, Fluxion AI, iFlytek Spark (Astron MaaS), and several other LLM providers. Concurrency for asset and clip rendering is configurable, defaulting to 1 (serial) for both; it also launches a CLI-only local video project workflow that supports version tracking and reuse of unchanged rendered outputs.

  4. Pika58

    Pika Redesigns Video Creation Experience with Video Studio and Direct Model Selection

    Pika has redesigned its entire video creation experience, allowing creators to work in their preferred generation style. For users who want to focus on creation without worrying about specific technology, Pika launched Video Studio; users with a preference for specific models can generate directly through those models. Pika also provided five video examples in different styles, showcasing the results of creators generating in their own way.

  5. The Decoder47

    Suno Adds Speech Feature: Generates Voice with Matching Background Music

    AI music generator Suno has launched a new feature called Speech, which can synthesize spoken text with matching background music into a single audio track. Users input their ideas or text and describe the desired voice tone and music style to generate content. The feature has been in limited testing for one month and can be used for poetry, meditation, and bedtime stories, though the beta version still has bugs—for example, British accents sometimes sound Australian. Suno has not disclosed how the model was trained. AI music generators are currently facing copyright infringement criticism, and several major record labels have sued Suno.

Oct 2Fri
  1. The Verge · AI58

    Suno launches voice generation feature, capable of producing vocals and background music simultaneously

    Suno has launched its voice generation feature, Speech, which is currently in open beta on both web and mobile platforms. It can generate vocals based on scripts or prompts while simultaneously producing matching background music. The feature offers two modes: Simple and Advanced. Advanced mode allows users to customize scripts and adjust AI voice gender, vocal style, and diversity per generation, with a maximum duration of approximately 8 minutes. Background music can be toggled off. Suno's Chief Product Officer Jack Brody stated that the feature is still not perfect and will continue to be improved based on user feedback.

  2. huobao-drama · 开源创作项目发布10

    Huobao v4.0.7 released: Unified brand icons and updated multi-platform installers

    Huobao has released v4.0.7, unifying the web logo, browser icon, and macOS and Windows application icons, and providing installers for macOS Apple Silicon, macOS Intel, and Windows x64. The macOS Apple Silicon installer has passed service and frontend startup checks, while other platforms have only completed packaging and content verification without corresponding system runtime testing.