Skip to content
Date and source

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

Nov 16Mon
  1. Zyphra · Zonos 语音模型66

    Zyphra releases ZONOS3-Mini multilingual TTS model

    Zyphra releases compact multilingual TTS model ZONOS3-Mini, supporting 43 languages, with approximately 100 million active parameters per token, and provides a native transformers port. The model uses ZAC-1 codec as audio tokenizer, includes 27 built-in release voices, supports voice cloning from short audio, and is licensed under Apache-2.0.

    Why it matters: ZONOS3-Mini is released as a native transformers port, supporting 43 languages and voice cloning, facilitating evaluation of its suitability as a multilingual TTS baseline.

Nov 13Fri
  1. Higgsfield 官方博客65

    How to Create a Faceless YouTube Channel with AI (Complete Guide)

    Higgsfield's official blog published a complete guide teaching creators how to create a faceless YouTube channel from scratch using AI, with the example channel being Statues With a Story. The guide clarifies YouTube's requirement to disclose realistic AI-generated content and lists the new thresholds for new applicants to enter full YPP starting February 1, 2027: 8,000 hours of watch time or 20 million Shorts views.

    Why it matters: This guide provides a complete process from topic selection to monetization, and clarifies YouTube's disclosure boundaries for AI-generated content and the new YPP thresholds for 2027.

Nov 12Thu
  1. HeyGen Updates64

    HeyGen Releases November 2026 Enterprise API Update

    HeyGen releases November 2026 enterprise API update: Video 1, Voice 1, and Image 1 are now available via API, enterprise rate limits have been increased, zero data retention coverage has been expanded, and v1/v2 will be retired on November 7, 2026. Video 1 supports text/image/reference video to video and generates dialogue and sound effects, Voice 1 supports Instant Clone and voice-to-voice, and Avatar V adds more natural blinking.

    Why it matters: The HeyGen enterprise API update unifies video, voice, and image models, increases rate limits, and requires migration to v3 after v1/v2 retirement.

Nov 11Wed
  1. WellSaid · 官方博客55

    WellSaid launches Producer, bringing voice production into the MCP era.

    WellSaid launches Producer, embedding professional voice production into agent workflows such as Claude, Copilot, and ChatGPT via an MCP server, and natively generates 48kHz audio. The platform supports agent style guides based on over 500,000 Oxford Languages transcriptions, open design, and digital human replication, with the license retained with the final audio.

Nov 10Tue
  1. Zyphra · Zonos 语音模型65

    Zyphra releases open-source speech model ZONOS3-Mini

    Zyphra releases open-source compact speech model ZONOS3-Mini, with approximately 100M active parameters, capable of real-time operation on phones, laptops, and browsers. The model supports cloning voices from audio samples, designing characters by age/accent/timbre, and word-by-word control of emotion, speaking rate, and expression. Weights are open-sourced under Apache 2.0, and it can be served via SGLang-Omni on NVIDIA GPUs with an OpenAI-compatible interface.

    Why it matters: With 100M active parameters, it can synthesize speech in real time in the browser, providing a locally runnable open-source solution for localized dubbing and character voices, supporting voice cloning and word-by-word emotion control.

Nov 6Fri
  1. Kapwing 创作指南64

    7 video editing tasks that can be automated with ChatGPT or Claude

    Kapwing tested automating seven types of video editing tasks with ChatGPT or Claude, covering editing planning, subtitle generation, translation dubbing, and B-roll production. In the test, Claude Code with FFmpeg built and rendered a 70.7-second YouTube Short, while Kapwing MCP completed AI dubbing in five languages. The article notes that standard chat interfaces cannot directly edit videos; actual editing requires a coding agent or an editor connected via MCP.

    Why it matters: The article provides seven types of automatable video editing tasks along with corresponding prompts and tool choices, allowing creators to build their own AI editing workflows based on them.

  2. Kapwing 创作指南65

    How to Use ChatGPT to Edit Videos (2026 Guide)

    Kapwing MCP connects ChatGPT to a video editing workspace, allowing users to complete editing tasks such as uploading, subtitling, translating, dubbing, and generating B-roll using natural language. In testing, a single combined request generated six exported versions (the original English version and five dubbed versions).

    Why it matters: Kapwing MCP allows ChatGPT to directly operate a video editing workspace. The tutorial demonstrates the complete natural language editing workflow from uploading, subtitling, translating, dubbing, to generating B-roll, and provides reusable prompt examples and cost references.

Nov 5Thu
  1. Luma News25

    MiniMax H3 alternatives: 7 omni-modal models that require no self-hosting

    MiniMax H3 requires a self-hosted GPU cluster; 7 omni-modal platforms can replace it without operations overhead. Luma Ray 3.2 leads, supporting multi-keyframe sequences, 1080p watermark-free export, and 4x faster generation, with direct export to Premiere, DaVinci, and Final Cut; Google Veo 3.1 can generate synchronized speech and sound effects in one pass, and ByteDance Seedance 2.5 targets multi-asset brand projects.

Oct 30Fri
  1. ElevenLabs 产品与研究60

    ElevenLabs launches SFX v3 sound effects model, now available on ElevenCreative and ElevenAPI

    ElevenLabs launches SFX v3 sound effects model, now available on ElevenCreative and ElevenAPI. SFX v3 handles prompts describing multiple sounds more reliably, produces more believable music and vocal generation, and delivers cleaner, more natural audio quality than SFX v2. Creators can use it in Flows, the Sound Effects tab, Studio, and Music Editor, while developers can integrate it via ElevenAPI.

    Why it matters: SFX v3 improves multi-sound prompt following, music and vocal generation, and audio quality, allowing creators to evaluate whether to replace their existing sound effects generation workflow.

Oct 29Thu
  1. 可灵官方博客71

    Ami discusses how Kling 4.0 brings subtle emotions to life.

    Kling invited creator Ami to use Kling 4.0 to produce the short film "Tea When You Have Time". She shared her experience using new capabilities such as 30-second generation, Omni Reference, and multi-keyframe. Kling 4.0 supports single-run 30-second generation, 21:9 aspect ratio, up to 10 keyframes, consistent 12-character assets, good lip-sync for Cantonese dialogue, and supports multiple dialects and English accents.

    Why it matters: Creator hands-on testing shows Kling 4.0 performs stably in 30-second long takes, 12-character consistency, and Cantonese lip-sync, providing a basis for evaluating an upgrade.

  2. HeyGen Updates67

    HeyGen Voice Launches Speech-to-Speech Feature

    HeyGen Voice launches a speech-to-speech (Speech-to-Speech) feature. Users can record a line with their phone or computer and get studio-quality voiceover that preserves emotion, rhythm, stress, and pronunciation, changing only the voice itself. The feature is now available on HeyGen and the API, supporting clean narration from casual recordings and offering a richer emotional range than text prompts, including whispers, laughter, and accents.

    Why it matters: HeyGen's speech-to-speech turns phone recordings directly into studio-quality voiceover, reducing repeated TTS generation, and creators can use it to evaluate the new voiceover workflow.

Oct 27Tue
  1. Runway 官方新闻74

    Runway launches App Studio, enabling no-code creation of custom creative apps.

    Runway launches App Studio, allowing users to describe their needs in natural language and build custom creative apps with standalone interfaces without code, generating images, videos, and audio. App Studio includes built-in apps such as Character Swap, AutoComp, and Product Portfolio, built on Brand Kits, Workflows, and Assets. It is included in all paid plans and consumes existing Runway credits.

    Why it matters: Runway's App Studio brings no-code app building into creative work, allowing teams to turn years of accumulated workflows and brand standards into tools anyone can use, reducing reliance on individual experts.

Oct 23Fri
  1. pyvideotrans 官方发布65

    pyvideotrans v4.17 released

    pyvideotrans v4.17 released, adding the Audio.cpp speech recognition channel, and adding noise reduction and vocal separation models based on audio.cpp. It also fixes the nemotronasr repeated download issue, adds the Opper translation channel, and adds a 'further simplify' option to subtitle translation.

    Why it matters: The new version adds the Audio.cpp speech recognition channel and noise reduction models, and optimizes the subtitle translation simplification option, suitable for evaluating upgrades to the video translation and dubbing workflow.

Oct 21Wed
  1. FastVideo 视频模型 · 模型发布80

    FastVideo releases ComfyUI version model weights for FastH3 Omni

    FastVideo released ComfyUI-usable weights for the final version of FastH3 Omni, providing two diffusion models, BF16 and INT8 ConvRot, which can generate video and synchronized audio from prompts and ordered image, video, and audio references.

    Why it matters: FastH3 Omni releases ComfyUI-usable BF16 and INT8 weights and provides the way to connect reference images, video, and audio, making it easier for creators to evaluate local video production pipelines.

Oct 20Tue
Oct 17Sat
  1. FastVideo 视频模型 · 模型发布60

    FastVideo releases FastH3-QAD-v2 video-audio model

    FastVideo releases FastH3-QAD-v2, an 8-step video and audio model trained with NVFP4 weights and quantization-aware distillation (QAD), runnable on a single Blackwell GPU (RTX 5090, RTX PRO 6000) or DGX Spark.

    Why it matters: The 8-step video and audio model lands on a single Blackwell GPU with NVFP4 quantized weights, and error data versus the BF16 teacher model is provided.

  2. ElevenLabs 产品与研究62

    ElevenLabs launches Instant Soundtracks in ElevenCreative

    ElevenLabs Launches Instant Soundtracks in ElevenCreative; After Uploading a Video, the Model Generates an Original Score and Analyzes Sound Effect Cue Points in the Footage, Automatically Placing Sound Effects on the Timeline at the Corresponding Timestamps.

    Why it matters: ElevenLabs merges score and sound effect generation into the video workflow, which can be used to evaluate the sound production stage of short dramas and ads.

Oct 16Fri
Oct 15Thu
  1. HeyGen Updates78

    HeyGen releases the HeyGen Voice speech model

    HeyGen releases a new speech model, HeyGen Voice, which it calls the first speech model built for video adaptation and which ranks first on the Artificial Analysis speech leaderboard; it is already included in every HeyGen video at no extra charge.

    Why it matters: HeyGen launches its first speech model for video adaptation, allowing creators to assess the room for replacing dubbing and multilingual lip-sync workflows.

  2. Fish Audio · 语音模型54

    Fish Audio releases Drama 3 int4 quantized version, reducing size to 22.1 GB and publishing WER evaluations

    An unofficial int4 quantized version, drama-3-int4, has appeared for Fish Audio's 35B (3B active) multi-speaker TTS model Drama 3, with a download size of 22.1 GB, lower than the original 41.5 GB. The expert layers, attention, and deltanet layers are quantized to int4, while the shared expert MLP remains in bf16.

Oct 14Wed
  1. HeyGen Updates22

    HeyGen October 2026 enterprise edition update: member usage limits, Video Agent collaboration, and Brand Glossary rebuild

    HeyGen's enterprise edition this month adds member usage limits and request features; administrators can set each member's usage quota, and members can directly request more quota within HeyGen with one-click approval. Video Agent supports team collaboration in the same session, with multiple people able to send prompts simultaneously while only one person edits at a time. Brand Glossary has been rebuilt, supporting per-language pronunciation and translation rules and CSV/Excel import and export; ElevenLabs is integrated as a single engine with a new v4 model option.

  2. HeyGen Updates42

    HeyGen October 2026 enterprise API update: Video 1.0 API, ElevenLabs v4, and Professional Voice Clone launch

    HeyGen released its October enterprise API update: the HeyGen Video 1.0 API is live, supporting short video generation from prompts, images, or reference materials. ElevenLabs v4 can be used for speech synthesis with per-request model selection, and Professional Voice Clone trains studio-grade voice clones based on HeyGen's proprietary speech model, supporting full-file or streaming output.

  3. Fish Speech 官方发布72

    Fish Audio releases the open-source speech generation model Drama 3 pre-release version

    Fish Audio releases the open-source speech generation model Drama 3 pre-release version, which can convert text into performed speech. The model uses a 35B-A3B hybrid linear attention MoE backbone (initialized from Qwen3.5) and a new codebook-MTP audio decoder; pretraining covers about 80 languages and dialects and hundreds of billions of tokens, and it supports multi-reference voice cloning, natural language instructions, multi-round revisions, multi-character scenes, speech infill editing, and long-audio and streaming synthesis.

    Why it matters: Open-source speech models put multi-character scenes, multi-round script revisions, and voice editing into the same model, allowing dubbing workflows to assess replacement potential accordingly.

Oct 13Tue
  1. pyvideotrans 官方发布40

    pyvideotrans v4.16 Released: Fixes Edge-TTS 403, Adds audio.cpp and fish.audio Dubbing Channels

    pyvideotrans released v4.16, fixing the Edge-TTS 403 issue and adding two new dubbing channels: audio.cpp and fish.audio API. This version also adds the Atlas Cloud translation channel, a French WebUI interface, and includes "use LLM to re-segment sentences instead of LLM error correction" in the advanced options for subtitle translation.

  2. Descript · 官方产品更新22

    Descript October update: global search, asynchronous recording requests, and ElevenLabs v4 voice cloning

    Descript released its October update, adding a search bar and a full results page to the entire cloud drive, and supporting Underlord in finding files, folders, projects, and layout packs. Enterprise cloud drives can send asynchronous recording requests, letting guests record on their own schedule and read scripts with a teleprompter; AI Speech has been upgraded to ElevenLabs v4, making voice clones closer to the real person.

Oct 12Mon
Oct 11Sun
  1. Kapwing 创作指南62

    How to Make Vox-Style Collage Animation with AI: A Step-by-Step Guide

    Kapwing published a step-by-step guide on using AI to generate Vox-style collage animation documentaries, broken into six steps: writing the script, breaking down visual beats, generating collage images, frame-by-frame animation, generating voiceover, and editing the final cut.

    Why it matters: A complete breakdown of the six-step AI workflow for Vox-style collage documentaries, including reusable image and animation prompts, ideal for creators looking to replicate the visual style.

Oct 9Fri
  1. Respeecher 官方博客38

    How to write AI voice rights into actor contracts (with template)

    Respeecher released a guide explaining that standard "name, voice, and likeness" clauses can no longer cover AI voice use, and that project-level digital replica consent clauses need to be added to actor contracts. The guide requires distinguishing between employment-based and independently created digital replicas as defined by SAG-AFTRA, and provides a template of the 7 clauses essential to an AI voice contract. California AB 2602 stipulates that a clause may be deemed unenforceable if it allows an AI replica to replace the actor's work, does not specify the use, and was not negotiated through legal or union representation.

  2. ElevenLabs 产品与研究36

    ElevenLabs launches synthetic voice detection in ElevenAgents and joins the Personal Agent Protocol working group

    ElevenLabs launched synthetic voice detection in ElevenAgents, which can analyze incoming call audio in the first few seconds of a call and determine whether it is a real person or AI-generated; enterprises can use this to set rules, such as prioritizing service for real customers, limiting the interaction scope of AI calls, and blocking cloned voices before sensitive operations.

  3. Synthesia · 官方博客62

    Synthesia Launches Syren: Generate Videos and Motion Graphics from a Single Prompt

    Synthesia released Syren, an AI video creation tool, in beta. By entering a prompt, a preset, or existing brand documents, images, videos, PPTs, or YouTube links, users can generate a finished video with motion graphics, animations, digital avatars, voiceover, music, and b-roll, and can make changes through conversation.

    Why it matters: Synthesia turns video generation into a conversational agent; compare how it and the existing editor divide work in scenarios requiring precise content.