{"id":7466,"date":"2026-08-19T19:10:06","date_gmt":"2026-08-19T19:10:06","guid":{"rendered":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/utilisation\/multimedia\/"},"modified":"2026-08-19T19:10:06","modified_gmt":"2026-08-19T19:10:06","slug":"multimedia","status":"publish","type":"wvn_doc","link":"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/utilisation\/multimedia\/","title":{"rendered":"Images, videos and voices"},"content":{"rendered":"<h1>Images, videos and voices<\/h1>\n<p>Beyond text, WivenLLM knows how to produce images and short videos, read<br \/>\nThese functions include: speaking answers aloud and transcribing speech.<br \/>\n<strong>optional<\/strong> : they only exist if an administrator has configured them.<\/p>\n<hr \/>\n<h2>Image generation<\/h2>\n<h3>Use<\/h3>\n<p>In a conversation:<\/p>\n<pre><code>\/image a schematic cross-section of a heat pump, technical style\n<\/code><\/pre>\n<p>The image appears in the conversation and can be downloaded. An agent can<br \/>\nalso generate an image during a task, if the skill<br \/>\nThe corresponding function is activated.<\/p>\n<h3>Configuration \u2014 <em>administrator<\/em><\/h3>\n<p><code>Settings \u2192 Image Generation<\/code>. Two types of suppliers:<\/p>\n<p><strong>Local<\/strong> \u2014 the models run on your machine, no data is sent out.<br \/>\nThis requires suitable hardware, in practice a graphics card.<br \/>\nSupported local installations also cover an integrated engine<br \/>\nmanaged by WivenLLM, which are image generation servers that you operate<br \/>\nAlready.<\/p>\n<p><strong>External<\/strong> \u2014 the main commercial image generation services are<br \/>\nYour description has been taken care of. It will then be forwarded to the chosen supplier.<\/p>\n<h3>Good to know<\/h3>\n<ul>\n<li>The generated images are attached to the conversation.<\/li>\n<li>Describe the <strong>style<\/strong> as much as the subject: &quot;technical diagram in black and white and<br \/>\n  &quot;White, white background&quot; gives a very different result from &quot;illustration&quot;.<\/li>\n<li>An image generation model cannot write readable text in a way<br \/>\n  reliable; don&#039;t expect visuals with exact labels.<\/li>\n<\/ul>\n<hr \/>\n<h2>Video generation<\/h2>\n<p>Same principle, with the command <code>\/video<\/code>.<\/p>\n<pre><code>\/video a slow-motion aerial view of a construction site, 5 seconds\n<\/code><\/pre>\n<p><strong>Realistic expectations:<\/strong> These are short sequences lasting a few seconds.<br \/>\ngeneration is long \u2014 from several minutes to much longer depending on the<br \/>\nsupplier and equipment \u2014 and much more demanding than image.<\/p>\n<p>The configuration is done in <code>Settings \u2192 Video Generation<\/code>, with the same<br \/>\nchoice between local execution and external service.<\/p>\n<hr \/>\n<h2>Listen to the responses (text-to-speech)<\/h2>\n<p>A play button appears under each answer.<\/p>\n<p><strong>Available options:<\/strong><\/p>\n<ul>\n<li><strong>Navigator&#039;s voice<\/strong> <em>(by default)<\/em> \u2014 uses the speech synthesis integrated into the<br \/>\n  System. No configuration, no data sent anywhere, quality<br \/>\n  variable depending on the operating system.<\/li>\n<li><strong>High-quality local voice<\/strong> \u2014 a downloaded engine that runs in the<br \/>\n  browser, more natural than system voice, still without network output.<\/li>\n<li><strong>External services<\/strong> \u2014 the main speech synthesis providers are<br \/>\n  supported for superior quality; the text of the answers is then<br \/>\n  transmitted to the supplier.<\/li>\n<\/ul>\n<p>Configuration in <code>Settings \u2192 Audio Preferences<\/code>.<\/p>\n<hr \/>\n<h2>Dictating messages (voice recognition)<\/h2>\n<p>A microphone button in the input area transcribes your speech into text.<br \/>\nBy default, the browser&#039;s speech recognition is used.<\/p>\n<blockquote>\n<p><strong>Important confidentiality point to be aware of:<\/strong> integrated speech recognition<br \/>\nbrowsers generally transmit the audio to the publisher&#039;s servers<br \/>\nbrowser. On an installation where everything needs to be local, it&#039;s a<br \/>\nData output not to be overlooked \u2014 check the browser&#039;s behavior<br \/>\nused, or disable the function.<\/p>\n<\/blockquote>\n<hr \/>\n<h2>Transcription of audio and video files<\/h2>\n<p>Distinct from dictation: when an audio or video file is imported as<br \/>\ndocument, it is <strong>transcribed<\/strong> then indexed like any other text.<\/p>\n<p>The built-in transcription engine is working <strong>locally<\/strong>, without a key or exit<br \/>\nnetwork. An external service can be substituted for it in<br \/>\n<code>Settings \u2192 Transcription preferences<\/code>.<\/p>\n<p><strong>Common uses:<\/strong> recordings of meetings, interviews, training sessions,<br \/>\nvoice messages. The transcript becomes searchable like a document.<br \/>\nordinary \u2014 \u00abwhat had been decided about the budget at the meeting on the 12th?\u00bb.<\/p>\n<p>To record a meeting directly from the application and obtain a<br \/>\nstructured report, see <a href=\"\/en\/wiven-llm\/docs\/utilisation\/reunions\/\">Meetings<\/a>.<\/p>\n<p><strong>Quality :<\/strong> depends on the clarity of the recording, the number of speakers and<br \/>\nOverlapping conversations. A recording of a meeting captured by a microphone.<br \/>\nLaptop computer gives inconsistent results.<\/p>\n<hr \/>\n<h2>What comes out of the network<\/h2>\n<table>\n<thead>\n<tr>\n<th>Function<\/th>\n<th>In local configuration<\/th>\n<th>In external configuration<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Image generation<\/td>\n<td>Nothing<\/td>\n<td>The description is sent to the supplier<\/td>\n<\/tr>\n<tr>\n<td>Video generation<\/td>\n<td>Nothing<\/td>\n<td>The description is sent to the supplier<\/td>\n<\/tr>\n<tr>\n<td>Text-to-speech<\/td>\n<td>Nothing<\/td>\n<td>The text of the response is sent to the supplier<\/td>\n<\/tr>\n<tr>\n<td>Voice recognition<\/td>\n<td>Depends on the browser \u2014 to be verified<\/td>\n<td>The audio goes to the supplier<\/td>\n<\/tr>\n<tr>\n<td>File transcription<\/td>\n<td>Nothing<\/td>\n<td>The file is sent to the supplier<\/td>\n<\/tr>\n<\/tbody>\n<\/table>","protected":false},"parent":7450,"menu_order":305,"template":"","meta":[],"class_list":["post-7466","wvn_doc","type-wvn_doc","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.6 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Images, vid\u00e9os et voix \u2014 Documentation WivenLLM<\/title>\n<meta name=\"description\" content=\"G\u00e9n\u00e9rer des images et des vid\u00e9os, dicter ses messages et \u00e9couter les r\u00e9ponses.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/utilisation\/multimedia\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Images, vid\u00e9os et voix \u2014 Documentation WivenLLM\" \/>\n<meta property=\"og:description\" content=\"G\u00e9n\u00e9rer des images et des vid\u00e9os, dicter ses messages et \u00e9couter les r\u00e9ponses.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/utilisation\/multimedia\/\" \/>\n<meta property=\"og:site_name\" content=\"Wiven AI\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/utilisation\\\/multimedia\\\/\",\"url\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/utilisation\\\/multimedia\\\/\",\"name\":\"Images, vid\u00e9os et voix \u2014 Documentation WivenLLM\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/#website\"},\"datePublished\":\"2026-08-19T19:10:06+00:00\",\"description\":\"G\u00e9n\u00e9rer des images et des vid\u00e9os, dicter ses messages et \u00e9couter les r\u00e9ponses.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/utilisation\\\/multimedia\\\/#breadcrumb\"},\"inLanguage\":\"en\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/utilisation\\\/multimedia\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/utilisation\\\/multimedia\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.wiven.ai\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Documentation\",\"item\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Utilisation\",\"item\":\"https:\\\/\\\/www.wiven.ai\\\/wiven-llm\\\/docs\\\/utilisation\\\/\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"Images, vid\u00e9os et voix\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.wiven.ai\\\/#website\",\"url\":\"https:\\\/\\\/www.wiven.ai\\\/\",\"name\":\"Wiven AI\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.wiven.ai\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Images, videos and voices \u2014 WivenLLM documentation","description":"Generate images and videos, dictate messages and listen to replies.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/utilisation\/multimedia\/","og_locale":"en_US","og_type":"article","og_title":"Images, vid\u00e9os et voix \u2014 Documentation WivenLLM","og_description":"G\u00e9n\u00e9rer des images et des vid\u00e9os, dicter ses messages et \u00e9couter les r\u00e9ponses.","og_url":"https:\/\/www.wiven.ai\/en\/wiven-llm\/docs\/utilisation\/multimedia\/","og_site_name":"Wiven AI","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/utilisation\/multimedia\/","url":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/utilisation\/multimedia\/","name":"Images, videos and voices \u2014 WivenLLM documentation","isPartOf":{"@id":"https:\/\/www.wiven.ai\/#website"},"datePublished":"2026-08-19T19:10:06+00:00","description":"Generate images and videos, dictate messages and listen to replies.","breadcrumb":{"@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/utilisation\/multimedia\/#breadcrumb"},"inLanguage":"en","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wiven.ai\/wiven-llm\/docs\/utilisation\/multimedia\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/utilisation\/multimedia\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.wiven.ai\/"},{"@type":"ListItem","position":2,"name":"Documentation","item":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/"},{"@type":"ListItem","position":3,"name":"Utilisation","item":"https:\/\/www.wiven.ai\/wiven-llm\/docs\/utilisation\/"},{"@type":"ListItem","position":4,"name":"Images, vid\u00e9os et voix"}]},{"@type":"WebSite","@id":"https:\/\/www.wiven.ai\/#website","url":"https:\/\/www.wiven.ai\/","name":"Wiven AI","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wiven.ai\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en"}]}},"_links":{"self":[{"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/wvn_doc\/7466","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/wvn_doc"}],"about":[{"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/types\/wvn_doc"}],"up":[{"embeddable":true,"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/wvn_doc\/7450"}],"wp:attachment":[{"href":"https:\/\/www.wiven.ai\/en\/wp-json\/wp\/v2\/media?parent=7466"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}