Skip to content
Date and source

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

Oct 2Fri
  1. Curious Refuge 创作教程55

    AI sound design tools tested: InVideo and ChatGPT Astra compared with human sound design

    Curious Refuge tested the AI sound design of InVideo and ChatGPT Astra on two projects and compared them with human versions. InVideo could identify some sound effect positions but executed them crudely with inconsistent volume; ChatGPT Astra's results were more usable but also fell short of professional standards. InVideo took about two hours and cost $4.56, while ChatGPT Astra took about 1 hour 45 minutes and cost $5.20.

Oct 1Thu
  1. 公众号:短剧内行人22

    Why did Huanyu Film and Television win two Golden Eagle micro-drama awards? An analysis of long-short synergy and its AI drama library layout

    The 16th China Golden Eagle TV Art Festival set up a micro-drama honor unit for the first time; "The Truth of Huge Amounts" produced by Yuvan Film and Television, a label under Huanyu Film and Television, won the annual micro-drama award, and contracted actor Liu Qing won the annual actor award. Huanyu uses a "long-short synergy, talent symbiosis" approach to align the production standards of long dramas and short dramas, and has launched the "AI Wanxiang Drama Library," collaborating with Xiaoyunque AI and Jimeng AI on concept films for three AI dramas, with over ten million plays and discussions across all platforms.

  2. Theoretically Media blog62

    Early Hands-On with Kling 4, Plus a Look at Gemini 4 Argon, Ideogram 4.5, and Eleven v4

    The author conducted hands-on testing of the Kling 4 early access version, which currently only offers the Flash model with 720p output, available to Ultra subscribers on annual plans; larger models are planned for October. Testing shows that Kling 4 appears to have resolved the lip-sync drift issue from 3.0, supports up to ten keyframe references, but performances are somewhat flat.

  3. Suno 官方博客62

    Suno releases the Speech audio model beta, capable of generating vocals and music simultaneously

    Suno released Speech beta, its first audio model that generates human voice and music together as a single complete track. Users input an idea, poem, or existing text, then describe the desired vocal tone and music style, and the system generates voice content with original background music. The model is now open to all users in beta; it had previously been tested with a small group of users for one month. The official statement notes that British accents occasionally drift toward Australian, and other effects still need improvement.

    Why it matters: Suno synthesizes voice and background music into a single track, allowing creators who do short-drama narration or dubbing to evaluate a new production approach.

Sep 30Wed
  1. 公众号:娱乐资本论22

    Bilibili danmaku AI judges, NetEase group-chat automatic enforcement: September internet patent roundup

    In September, major internet companies published patents密集ly: Bilibili applied for a livestream interaction patent that uses large models combined with danmaku to generate virtual judge commentary; NetEase applied for a group management patent where, after the group owner writes group rules, the system automatically parses them and issues real-time warnings and mutes. Youku is working on one-click script-to-storyboard splitting and video character expression editing, Baidu's ERNIE large model uses multi-agent automatic drafting and revision, Alibaba's Tongyi Wanxiang accelerates AI image generation, and Kuaishou's Kling diagnoses text-to-image shortcomings through layered analysis.

Sep 29Tue
  1. DramaClip · 公开创作工具发布80

    DramaClip v0.2.0 First Public Release: Import Short Dramas to Batch-Generate Promotional Short Videos

    DramaClip v0.2.0, the first public release, allows users to import a short drama with dozens of episodes and batch-generate ready-to-publish promotional short videos, with all media processing completed locally. This version uses OCR and ASR fusion transcription with hard-subtitle character-by-character correction—60% of segments were corrected in testing—and employs CAM++ voiceprint clustering for speaker diarization.

    Why it matters: A short-drama promotional video tool that completes transcription, narration scripts, and voice cloning locally—explore its nine output modes and cut-point alignment approach.

  2. VibeClips · AI视频创作教程22

    Which AI Video Models Can Generate Voice and Sound Effects: A Complete Breakdown of VIBE's Audio Models

    Over half of the video models on VIBE can generate audio, divided into three categories: always-on native audio, toggleable audio, and support for uploading user-provided recordings. Sora 2, WAN 2.6/2.7, Veo 3 Fast, and Seedance 2.5 always produce audio; Veo 3.1, Kling 3, and PixVerse 6 feature audio toggles; WAN 2.7, PRUNA V, and Talking Avatar accept user-uploaded voice or music files.

  3. 福建省广电局 · 媒体报道22

    Original Micro-Drama *The Lost Navigation Chart* Premieres, Blending Sci-Fi AI with Maritime Silk Road History

    Original micro-drama *The Lost Navigation Chart* premiered on September 24 on the Yangshipin client and platforms including Douyin, Hongguo, iQiyi, and Youku, co-produced by China Central Television's Yangshipin and the Quanzhou Municipal Committee Propaganda Department. The drama is the second installment of the first-season micro-drama trilogy for 'The Eastern Grand Port,' filmed simultaneously in both landscape and vertical versions. The landscape version consists of 30 episodes and is based on the Yuan Dynasty navigator Wang Dayuan and his work *Dao Yi Zhi Lue*, centering on a young Quanzhou-born AI scientist whose intelligent model 'Zhiyuan' restores lost ancient texts and deduces historical truths.

  4. drama-skills · 公开创作项目发布48

    v0.8.1 Released: Still-Frame Editing, Character Voice Binding, and Tested Prompting Methods

    The static comic drama tool v0.8.1 adds still-frame editing, allowing direct editing from keyframes and voiceover into a finished video, with support for mixed still-frame and video editing, push-pull and panning, continuous camera movement by speed, and voiceover and subtitles across cut points. The video prompt adds a reference audio field, reconciled with the character voice reference in the visual settings, compiled as reference_audio during production, and must be bound to the speaking character in the shot. This version also supplements, based on small-sample testing, prompting methods for reaction shots, two-person contact, keyframe art style, and TTS tone; the conclusions are limited to the samples and conditions in the records.

  5. mlx-audio · 开源创作项目发布8

    mlx-audio v0.5.7 Released

    mlx-audio released v0.5.7, submitted by lucasnewman, with 56 commits on the main branch since the previous version. This update bumps the version number to 0.5.7 and removes a redundant soundfile reference.

Sep 28Mon
Sep 26Sat
  1. note · ai_freak · 图像视频创作分享52

    How to unify characters and character voices in AI animation

    AI FREAK shares two approaches to unifying character voices in AI animation: one is to first generate the voice with Ondoku-san or ElevenLabs and then use Kling or HeyGen for lip sync; the other is to write the dialogue into the prompt when generating video with Seedance 2.5 so it is generated together. The author uses the second approach in the self-made 3DCG animation "BRAIN BUSTERS," but the same character still shows timbre changes across different shots, so the character features along with the voice timbre are written out to about 800 characters to fix the voice.

Sep 25Fri
  1. GitHub:AI视频开源项目发现78

    SeeCut: Open-Sourced Auto-Editing Skill for Digital Human Voiceover, Built for Coding Agents

    YeJe-cpu open-sourced SeeCut on GitHub, a skill for coding agents like Claude Code that automatically edits digital human or real-person voiceover footage into vertical short videos with motion effects, and can optionally push the result as a layered CapCut draft for fine-tuning.

    Why it matters: The author open-sourced a reusable voiceover editing skill covering the full workflow from digital human voiceover to CapCut draft delivery.

  2. AI Business42

    Google Adds TTS Models to Gemini 3.8, Strengthening Voice AI Capabilities

    On September 23, Google launched Gemini 3.8 TTS and Gemini 3.8 Flash-Lite TTS, calling them the most capable audio generation models available today. The former is aimed at creative direction and character design, capable of generating new voices from scratch using natural language prompts, covering scenarios such as games, audiobooks, and podcasts, and supporting customization of characters, accents, and voice features across more than 100 languages and dialects; the latter is used for AI dubbing, content creation, and voice agents.

Sep 23Wed
  1. Google DeepMind72

    Google Releases Gemini 3.8 Flash TTS and Flash-Lite TTS

    Google DeepMind has released two speech synthesis models: Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. The former is designed for character design and line-by-line performance direction, while the latter targets high-volume, low-cost dubbing and voice agent scenarios.

    Why it matters: The two TTS models transform voice generation from fixed presets into a line-by-line directed creative workflow, enabling dubbing and audiobook teams to evaluate migration accordingly.

  2. YouTube 官方博客48

    YouTube Releases a Suite of New Tools for Creators and Viewers

    YouTube unveiled a batch of new tools at the Made on YouTube event, covering creation, live streaming, and monetization. The Shorts and YouTube Create apps now include a conversational editing tool, and YouTube Studio supports video A/B testing with up to three versions compared. Live adds live battles and real-time auto-dubbing, while likeness detection is coming to mobile.

  3. Cartesia 官方博客62

    Cartesia launches Multilingual Voices, with 50+ voices natively supporting up to 25 languages

    Cartesia launched Multilingual Voices, where 50+ voices in the library can natively speak up to 25 languages, and supports extending custom voice clones to multilingual. Each language and accent is scored by native speakers using a rubric, checking whether accents are maintained and whether dates, numbers, and currencies are handled according to local conventions.

    Why it matters: Cartesia extends the same voice to 25 languages and supports cloning with 10 seconds of audio followed by adding multilingual accents, allowing teams doing multilingual dubbing to evaluate replacing their existing workflows.

Sep 21Mon
  1. GitHub:AI视频开源项目发现62

    Tencent Hunyuan Open-Sources Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation

    Tencent Hunyuan, in collaboration with Fudan University and Zhejiang University, proposed Prism, a dynamic sparse attention framework for natively training 2K joint video-audio generation models. It organizes token sequences into spatiotemporal macro-blocks and dynamically allocates block shapes based on local content, achieving a 2.5x training speed improvement over full attention with higher generation quality.

  2. pyvideotrans 官方发布38

    pyvideotrans v4.13 Released: Optimized Model Download Retry and Whisper Sentence Segmentation, Added Doubao TTS 2.0 Voiceover Characters

    pyvideotrans v4.13 released a Windows pre-packaged version with automatic retry after model download failures and an optimized re-segmentation algorithm for Whisper model recognition. This version improves speech recognition, subtitle translation, and speech synthesis model support for SiliconFlow, Minimax, and OpenRouter, adds Doubao TTS 2.0 voiceover characters, and restructures the settings window and menu architecture. Local voiceover channels such as Qwen-TTS and Higgs have dropped 8-bit quantization, and the media merge function now includes a pause button.

Sep 20Sun
  1. 小智博客 · 音视频实践38

    Jianying Pro Video-to-Text Tutorial: Smart Subtitle Recognition and Subtitle Export Tested

    Jianying Pro (Windows and Mac clients) has built-in smart subtitles that can directly recognize on-screen speech into a subtitle track, ideal for footage that will be fine-cut in Jianying anyway. The tutorial uses an eight-minute product explanation video with Chinese subtitles as an example, testing the smart subtitle recognition and subtitle export workflow.

Sep 18Fri
  1. VibeClips · AI视频创作教程22

    VIBE Tutorial: How to Create AI Digital Human Talking-Head Videos with Talking Avatar

    VIBE's Talking Avatar model requires only a frontal photo and a voice recording to generate a 480p or 720p lip-synced digital human talking-head video, with no text prompt needed, and the output language follows the recording. The model is billed per use: 35 tokens for 480p and 60 tokens for 720p, regardless of recording length, and the output aspect ratio is locked to that of the uploaded photo.

  2. WellSaid · 官方博客22

    How to Localize Marketing Campaigns with AI Voice

    WellSaid's official blog published a guide on how to localize marketing campaigns with AI voice. The process includes preparing localized scripts, selecting voices with regional accents and dialects for each market, generating and previewing voiceovers, adjusting pronunciation and pacing, and then reusing the same creative direction across markets. AI voice lets teams avoid rescheduling recording sessions for every script change, shifting time and budget from coordinating recordings to comparing and polishing versions.

  3. Descript · 官方产品更新22

    Descript September update: subtitle presets and animations, AI-generated music and sound effects, multi-currency payments

    Descript released its September update: subtitles gain 18 presets and 10 text animations, plus search and filtering; AI can generate background music and sound effects from a description, requiring an upgrade to version 145.0.15 or newer. Checkout adds Apple Pay, Google Pay, Cash App and other payment methods and displays local currency, the voice library switches to ElevenLabs, and jump-cut smoothing changes to per-second billing (audio 0.5 AI credits/second, video 1.0/second).

Sep 17Thu
  1. Creator Animation · AI影片制作教程18

    A guide to building an AI filmmaking tool stack for content monetization

    Creator Animation offers an on-site AI Film Studio where creators can use prepaid credits to directly generate multi-scene films and keep 80% of their work's revenue under an 80/20 split. The platform has no ad interruptions or algorithmic review thresholds, viewers can watch for free, fans can buy a $9/month Download Pass for offline saving, and creators start with 10GB of free storage.

Sep 16Wed
  1. Epidemic Sound28

    Epidemic Sound and Oxford VGG launch the audio retrieval framework AuroLA, now live for sound effect search

    Epidemic Sound and the University of Oxford's VGG have launched the audio-text retrieval framework AuroLA, based on the open-source Qwen2.5-Omni-7B, using a multimodal large model as both the fast retrieval and reranking backbone, surpassing the previous state of the art on all tested benchmarks with roughly 1% of the training data of comparable systems. The framework is already in production, powering Epidemic Sound's sound effect search, and a manually annotated validation benchmark of 1,297 sound effects has been open-sourced under the CC BY-NC-ND 4.0 license.

Sep 15Tue
Sep 14Mon
  1. Cartesia 官方博客22

    TTS models and voices are not the same thing: Cartesia breaks down fixed-speaker, multi-speaker, and voice cloning

    Cartesia's official blog points out that a TTS model and the voice it uses are two separate concepts, with the voice being more like an input than the model itself. Fixed-speaker models receive only text, multi-speaker models can additionally select preset voices, and zero-shot cloning models accept 10 to 60 seconds of reference audio as a prompt; Cartesia's Sonic end-to-end model supports Instant Voice Cloning. Professional voice cloning (PVC) requires fine-tuning the model with a larger recording dataset and can take hours.

Sep 10Thu
  1. OpenAI News62

    OpenAI launches GPT-Live-1 voice model in the API

    OpenAI launched GPT-Live-1 in the API, supporting natural full-duplex voice conversations. The model has improved instruction following and supports custom voices and telephony capabilities.

    Why it matters: OpenAI opens full-duplex voice conversation capabilities to the API, giving developers a way to evaluate how to integrate voice interaction products.

Aug 11Tue
Jul 15Wed
  1. Hugging Face Blog36

    Real World VoiceEQ Released: Measuring the Human Quality of Voice AI

    The voice AI evaluation benchmark Real World VoiceEQ has been released, covering 40+ mainstream closed-source and open-source voice models, 15+ evaluation dimensions, and 60+ metrics, spanning ASR, TTS, S2S, and voice understanding. The benchmark is built on over 1 million human ratings, including 785,000 TTS ratings and 48,000 STS ratings. Evaluations show that no system configuration in TTS ranks in the top five across all eight capability groups, indicating that voice models are stronger at "speaking" than at "listening."

Jul 1Wed
Jun 9Tue
  1. Google DeepMind71

    Google Releases Gemini 3.5 Live Translate Real-Time Voice Translation Model

    Google has released the audio model Gemini 3.5 Live Translate, supporting near real-time speech-to-speech translation across 70+ languages, with automatic language detection and preservation of the speaker's tone, rhythm, and pitch.

    Why it matters: Gemini 3.5 Live Translate reduces simultaneous interpretation latency to a few seconds and supports 70+ languages, enabling developers to evaluate real-time dubbing and meeting translation solutions.

May 7Thu
May 4Mon