ElevenLabs announces SFX v3 is now available. Users can access it in creative tools including Flows, the sound effects panel, Studio and the music editor. It is also offered through the ElevenAPI and the ElevenLabs mobile app.
Inworld has rolled out two updates to Realtime TTS-2. The optional Reasoning feature has the model write performance directions from context before synthesis. The updated model keeps the existing model ID. According to Inworld's comparison with the previous version, short utterances generate about 13% faster and medium-length ones about 9% faster, and cloned-voice similarity has improved along with fewer dropped words in long text. TTS-2 currently supports single and asynchronous synthesis, with WebSocket streaming, duplex and batch synthesis coming soon.
Why it matters: Instead of fixed emotion tags, it lets the model write its own performance directions from context, though WebSocket streaming and full-duplex access will come later.
Google DeepMind has unveiled Genie 4, a next-generation world model that generates interactive simulated worlds in real time, with native audio and conversational interaction. Users can change the weather or camera angle, or add characters and objects, using natural language, and Gemini adjusts prompts to keep the scene coherent. It is currently available as a research preview to trusted testers. Google AI Ultra subscribers and early Gemini API partners will gain access in the coming weeks, though visual detail and object persistence may still drift over time.
Why it matters: It puts native audio, real-time steering, and Gemini reasoning into a single world simulation, offering a look at viable paths for interactive world models.
In the Roblox Studio beta, AssetService:CreateAssetAsync can convert an AudioTextToSpeech object into a speech audio asset. Developers can generate speech in Studio ahead of time instead of calling text-to-speech at game runtime, which lets speech respond instantly and avoids API rate limits. Generated assets currently cannot have a custom name, description, or creator ID, and are all named TTS_Asset_ followed by the asset ID.
Why it matters: This update moves speech generation from game runtime to the Studio editing stage, which may be useful for developers weighing the cost of adding voice content and the limits of the API.
fal adds HeyGen Video and HeyGen Voice models. Video clips include built-in dialogue, ambient sound, and sound effects, with text-to-video, image-to-video, and reference-image video generation at 5 to 15 seconds per clip and up to 2K. Voice supports 39 languages and instant voice cloning, with a faster Turbo tier.
Why it matters: The clip length, resolution, and language count given in the announcement are fairly specific, making it easy to compare with other video and voice generation tools.
Inworld provides voice synthesis and model inference for Latitude's game Voyage, so every story beat can be narrated with character voices. In the case study, voice costs are about a quarter of Latitude's previous provider's, and TTS runs 3–5 times faster than another provider in Latitude's production tests. Over six weeks, the platform handled more than 15 million TTS calls and 25 million inference calls.
Why it matters: The case study offers vendor-disclosed figures for voice costs, TTS speed, and call volume, which can be used to weigh the cost and infrastructure trade-offs of fully narrating a game.
Why it matters: The guidelines cover details such as consent for training, compensation for replicas, and cross-border translation, and can be read alongside the SAG-AFTRA agreement provisions mentioned in the article.
UKIE and Sheridans have launched an AI compliance and accreditation service to help UK game studios use AI lawfully and responsibly. The service involves a four-step process and ends with the UKIE accreditation mark, which studios can use in fundraising and business negotiations to demonstrate compliance and due diligence.
Why it matters: Lawyer Anna Poulter-Jones outlines the main legal risks game studios face when using generative AI, covering training data infringement, licensing of inputs and outputs, data privacy, copyright ownership of AI-generated content, and labeling of deepfakes.
ElevenLabs has launched Instant Soundtracks. After you upload a video, the model generates original background music and adds sound effects at suitable moments. You can also use the video's original audio as a reference so the new soundtrack stays close in style. The feature is now available on ElevenCreative, ElevenMusic, and ElevenAPI.
Why it matters: The feature is aimed directly at video creators. It generates original music and sound effects in a single pass, and is worth comparing against existing video post-production workflows.
ElevenLabs has launched Eleven v4 and Eleven v4 Turbo voice models. The official post it quotes calls them the company's fastest and most emotionally expressive voice models, and says they rank first on Artificial Analysis. This item's body text is only a link to the original v4 post.
According to company registration data, Kurogames invested in Yanzhi Domain Technology (Shenzhen) Co., Ltd., holding a 15% stake—Kurogames' first AI company investment. Founded in 2024, Yanzhi Domain's products include Vocu, an AI audio creation platform, and Genyu TalkiVerse, an interactive 3D AI character platform for scenarios like game NPCs. The article also notes that miHoYo, Qihoo, and Giant Network have increased AI investments in recent years across large models and AIGC.
Why it matters: The article contextualizes Kurogames' investment within Tencent's holdings and continued industry bets on AI by gacha publishers, making it a good reference for understanding the broader trajectory of Chinese gaming companies' AI investments.
Mirelo SFX V2.0 is now live on fal, generating sound effects from text prompts or video input. It can replace unwanted music and sounds while preserving dialogue, and produce coherent sound effects and ambient audio across video cuts.
Why it matters: Beyond text prompts, it can generate sound effects from video input and replace unwanted music and sounds while keeping dialogue intact.
Kuro Technology has become a new shareholder in Yanzhiyu Technology with a 15% stake, and Kuro founder Liu Sheng has joined Yanzhiyu's board of directors. This is Kuro's first public investment in the AI field. Yanzhiyu focuses on hyper-realistic voice and 3D character driving systems, and multiple sources say its angel round carries a valuation of about 200 million yuan. The article notes that the next thing to verify is whether its voice and 3D driving models can be integrated into Kuro's game engine and projects in development.
Why it matters: The article places this investment within the broader data on AI investment in the game industry, showing readers how game companies are extending character performance capabilities down into underlying technology.
Youxituoluo interviewed Ximing, chief director of Xingcunzhe Biji, and Yizhou, CEO of publisher Shenmi Huangguan, who said the title took about 4 months from the start of production to packaging, was made by a team of 6 people, and uses roughly 700 minutes of video footage. Based on the market price of 2,000 yuan per minute, the video portion alone is estimated at about 1.4 million yuan, excluding live-action voice acting and game packaging. Ximing said the team's effective shot rate for AI video was about 20%, and the script was mainly written by hand.
Why it matters: The interview lays out production details for a 6-person team finishing 700 minutes of video in about 4 months, along with a cost estimate and the effective shot rate, which can be used to judge the production threshold for AI interactive film games.
Roblox has brought the team behind AI audio startup Audioscape into the company, with its technology to be natively integrated into Roblox's creator tools. The AI audio search and discovery tools Audioscape developed let creators find sound effects by how they actually sound rather than by name; it recently also built an AI Audio Agent spanning audio discovery, sound design, audio programming, mixing and testing, with the goal of bringing Roblox creators closer to AAA-level audio production.
Why it matters: Roblox has brought the Audioscape team in-house, and its audio tools that retrieve sounds by their characteristics will be built in as a platform creation capability, offering a way to observe changes in the platform's audio production pipeline.
The driving-instructor simulation game Jiao Meimei Kai Che, developed by the four-person indie team Easy Fox, has gone viral on Steam and social platforms, with playtest players growing more than 20-fold in a month. Because the sister's voice is generated in real time by a cloud large language model, daily AI service costs have exceeded 160,000 yen (about RMB 7,000), leaving the team's finances on the verge of collapse; it has applied for a bank loan to keep its servers running and admits the demo may be taken offline early.
Why it matters: The indie team was dragged into debt by cloud large-model token costs when players flooded in, exposing the cost-structure problem that real-time AI dialogue gameplay faces on the business side.
Why it matters: This weekly recap focuses on updates including animation state machines, collision data, and TTS auto-translation, so developers can judge which features have entered Studio Beta.
LiveSynth is a streaming neural synthesizer that supports zero-shot instrument cloning and text-to-instrument generation, and can be played interactively in real time. It uses a feedback-free causal Transformer conditioned on MIDI events and CLAP timbre embeddings to output continuous audio latents at 100 Hz, which a causal variational autoencoder then decodes into audio; frame-level timbre conditioning enables continuous timbre morphing, and MIDI conditioning dropout allows autonomous continuation from a performance prefix.
Why it matters: The paper sets out the architecture and real-time performance data of a streaming neural synthesizer, useful for understanding low-latency generation for playable instruments.
Roblox announced that it is adding automatic translation to its text-to-speech (TTS) API, so players will hear voices generated in their own language. AudioTextToSpeech gains a new AutoLocalize property that defaults to true: Roblox detects the language of the input text and compares it against the language settings of players in the server, and when the two differ and both are supported by TTS, it automatically translates the text and routes it to the preset voice with the closest characteristics.
Why it matters: Integration only requires leaving the default AutoLocalize enabled, but automatic translation currently covers only AudioTextToSpeech dynamic audio; TTS assets are still planned.
During the Mid-Autumn Festival, Zaomeng Ciyuan's AI streamer Ziying took on a time-limited broadcast challenge in her live room; the real-time interaction model behind her is Vidu S2, released not long before, and the room drew as many as 20,000 viewers at one point. Ziying has no fixed script: viewers can request songs, vote on her look and send gifts, and she has to change outfits and perform while interacting, then pick up where she left off after being interrupted. The author also tested Vidu S2's Avatar and Editing: uploading a real person's photo or an anime image and adding some settings creates a digital human, and switching on the camera allows real-time outfit changes, art style changes and background swaps while filming.
Why it matters: Using a livestream hosted by an AI streamer with no fixed script as a case study, it tests Vidu S2's real-time interaction and outfit-switching abilities, and discusses how they could be applied to game NPCs.