{"rewrite":{"id":"r_ddcb7b825f5c9a23fdff5d77","clusterId":"c_02acbad09b6de3a2cc521fb7","slug":"nizima-live-2-7-adds-ai-assistant-and-voice-only-model-control","model":"deepseek-v4-flash:free","headline":"nizima LIVE 2.7 Adds AI Assistant and Voice-Only Model Control","summary":"Live2D Inc. released version 2.7 of its VTuber tracking app nizima LIVE on August 12, 2026. The update adds an AI assistant feature that links a Live2D model to a chat AI service such as ChatGPT, Gemini, or a local LLM, allowing users to converse with the model by text or voice. The assistant's speech output uses the VOICEVOX series, with 31 characters and 82 total voices including Zundamon and Shikoku Metan. The model's mouth and body move in sync with the speech, and emotions estimated from the conversation are reflected in facial expressions. Responses can be output as subtitles to OBS for display on a streaming screen. The AI assistant function is currently available only in Japanese. The update also adds a voice tracking function that moves the model using only voice input, without a camera, for eye blinks, mouth movements, and full-body motion. Other additions include a time parameter function linked to real-world time, lip sync support for all models on macOS, mouse click assignment to shortcuts, and Google account login. New sample models for Zundamon and Shikoku Metan are included, illustrated by Sakamoto Ahiru.","whyItMatters":"The AI assistant feature positions nizima LIVE as a tool for automated streaming content, letting VTubers run interactive chat sessions without manual model control, which could change how solo streamers produce content.","webCardHtml":"\u003cp\u003eThe release notes detail how the AI assistant is set up: users open the \u0026#34;Model List\u0026#34; then the \u0026#34;AI Assistant\u0026#34; tab, pick a model, and click \u0026#34;Add.\u0026#34; The first run requires an API key for the chosen chat AI plus a download of the selected voice model. Live2D states that model data is not sent to the chat AI and is not used for learning, while chat content and character settings are sent to the connected AI and handled under that service\u0026#39;s terms. The company plans continued updates to the assistant feature.\u003c/p\u003e\n\u003cp\u003eOther additions in 2.7 include three new effects, \u0026#34;Mirror Ball,\u0026#34; \u0026#34;Comic,\u0026#34; and \u0026#34;Pixel Art,\u0026#34; plus a menu that places selected items to match the screen\u0026#39;s vertical or horizontal width. Expression and motion editing now lets users snap to key values by right-click dragging when overwriting, and the parameter settings input preview can be dragged to check values directly. Webcam face detection wobble at the edge of its range is reduced, and tracking performance is improved.\u003c/p\u003e\n\u003cp\u003eThe press release also touts nizima LIVE as usable by beginners with just a webcam and PC, and notes that modelers familiar with Live2D can adjust model movements in fine detail. The update applies to the Windows and macOS desktop app, with nizima LIVE TRACKER for iOS also available.\u003c/p\u003e","blueskyPost":"nizima LIVE 2.7 lets you link a Live2D model to ChatGPT or Gemini and talk to it by voice, with the model's face reacting to the conversation. Japanese only for now.","twitterPost":"VTuber app nizima LIVE now has voice-only tracking: no camera needed to move the model's eyes, mouth, and body. Also adds mouse-click shortcuts and Google login.","threadsPost":null,"newsletterBlurb":"Live2D's VTuber app nizima LIVE updated to 2.7, adding an AI assistant that connects models to chat AI services like ChatGPT, with VOICEVOX voices and OBS subtitle output. The update also introduces voice-only model tracking and time-linked parameters.","attributionJson":"[{\"source\":\"ASCII.jp\",\"url\":\"https://ascii.jp/elem/000/004/426/4426507/?rss\",\"title\":\"AI アシスタント機能・音声入力のみでモデルを動かせる機能ほか／Live2D公式VTuber用アプリ「nizima LIVE」がアップデート！\"},{\"source\":\"Denfaminicogamer\",\"url\":\"https://news.denfaminicogamer.jp/news/2608122v\",\"title\":\"AI Assistant Feature Added to 'nizima LIVE,' an App That Lets Anyone Easily Move Live2D Models; Chat with Your Favorite Live2D Model and Talk by Voice\"},{\"source\":\"PANORA\",\"url\":\"https://panora.tokyo/archives/152492\",\"title\":\"Live2D Official VTuber App \\\"nizima LIVE\\\" Updated: AI Assistant Function and Voice-Input-Only Model Control Added\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":28582,"outputTokens":1424,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1786583872,"createdAt":"2026-08-13T01:08:44.000Z","publishedAt":"2026-08-13T01:16:44.000Z","updatedAt":"2026-08-13T01:08:44.000Z"},"cluster":{"id":"c_02acbad09b6de3a2cc521fb7","canonicalTitle":"Live2D公式VTuber用アプリ「nizima LIVE」がアップデート　AI アシスタント機能・音声入力のみでモデルを動かせる機能が追加","representativeArticleId":"a_492a210da2c382b582f750e3","sourceCount":3,"writtenSourceCount":3,"writeAttempts":0,"isSolo":false,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[\"nizima LIVE\"],\"studios\":[\"Live2D\"],\"people\":[],\"type\":\"news\",\"domain\":\"vtuber\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-08-12T08:47:02.000Z","lastSeenAt":"2026-08-12T10:11:19.000Z","updatedAt":"2026-08-13T01:16:45.000Z"},"attribution":[{"source":"Denfaminicogamer","url":"https://news.denfaminicogamer.jp/news/2608122v","title":"誰でも手軽にLive2Dモデルを動かせるアプリ『nizima LIVE』にAIアシスタント機能が追加。好きなLive2DモデルをチャットAIと連携し、声での会話も可能"},{"source":"ASCII.jp","url":"https://ascii.jp/elem/000/004/426/4426507/?rss","title":"AI アシスタント機能・音声入力のみでモデルを動かせる機能ほか／Live2D公式VTuber用アプリ「nizima LIVE」がアップデート！"},{"source":"PANORA","url":"https://panora.tokyo/archives/152492","title":"Live2D公式VTuber用アプリ「nizima LIVE」がアップデート　AI アシスタント機能・音声入力のみでモデルを動かせる機能が追加"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":["nizima LIVE"],"studios":["Live2D"],"people":[],"type":"news","domain":"vtuber","is_roundup":false},"keyFacts":["nizima LIVE 2.7 was released on August 12, 2026, by Live2D Inc.","The AI assistant feature supports chat AI services including ChatGPT, Gemini, and local LLMs, and is currently available only in Japanese.","The AI assistant's speech output uses VOICEVOX series voices, with 31 characters and 82 total voices including Zundamon and Shikoku Metan.","The voice tracking function moves the model using only voice input, without camera tracking.","The time parameter function links a time input to Live2D parameters, with cycles selectable between 24 and 12 hours."]}