Guide for administrators. General information and licensing: Libretto Work<\/a>.<\/p>\n\n Libretto reads answers aloud. By default the iOS system voice speaks locally on the device<\/strong>, so no text leaves the device. Users can optionally enable a cloud voice (OpenRouter, with their own key). Answer texts then go to that service. As an organization you can define which speech output is allowed.<\/p>\n Important:<\/strong> Employees cannot loosen<\/strong> a policy of the organization. Local settings or rules in the app can only restrict it further. What all<\/em> sources (device management, server, local rule) allow is permitted. The system voice is always allowed.<\/p>\n Two ways, which can be combined:<\/p>\n\n For organizations with device management (Microsoft Intune, Jamf, Workspace ONE and others). The configuration applies to the whole app on the managed device, employees cannot change it, and changes arrive live in the app. App bundle ID: Example 1:<\/strong> only the local system voice, on the whole device.<\/p>\n Example 2:<\/strong> only your domain gets the system voice, employees’ private profiles stay unaffected.<\/p>\n In Microsoft Intune:<\/strong> Apps \u2192 iOS\/iPadOS \u2192 App configuration policies \u2192 Add \u2192 Managed devices<\/em>, select the Libretto app and choose “Enter XML data” as the format. Enter the For organizations without device management. Your server delivers a small JSON file at<\/p>\n nginx:<\/strong><\/p>\n Apache:<\/strong><\/p>\n Technical questions: support@computeq.de<\/a> As of: 7 October 2026<\/em><\/p>\n","protected":false},"excerpt":{"rendered":" Libretto Work: restricting speech output Guide for administrators. General information and licensing: Libretto Work. What is this about? Libretto reads answers aloud. By default the iOS system voice speaks locally on the device, so no text leaves the device. Users can optionally enable a cloud voice (OpenRouter, with their own key). Answer texts then go<\/p><\/div>\nWhat is this about?<\/h2>\n
Way A: Managed app configuration (MDM)<\/h2>\n
net.keutgen.libretto<\/code>.<\/p>\n\n
Key<\/th> Type<\/th> Meaning<\/th><\/tr><\/thead>\n speechAllowedEngines<\/code><\/td>Array of strings<\/td> Allowed speech output for all<\/strong> profiles. Values: system<\/code>, openrouter<\/code><\/td><\/tr>\nspeechRules<\/code><\/td>Array of objects<\/td> Allowed speech output per domain<\/strong>: host<\/code> (domain, subdomains count) and allowedEngines<\/code><\/td><\/tr>\n<\/tbody>\n<\/table>\n<dict>\n <key>speechAllowedEngines<\/key>\n <array>\n <string>system<\/string>\n <\/array>\n<\/dict><\/code><\/pre>\n<dict>\n <key>speechRules<\/key>\n <array>\n <dict>\n <key>host<\/key>\n <string>firma.de<\/string>\n <key>allowedEngines<\/key>\n <array>\n <string>system<\/string>\n <\/array>\n <\/dict>\n <\/array>\n<\/dict><\/code><\/pre>\n<dict><\/code> from one of the examples. In Jamf<\/strong> you enter the same under the app’s App Configuration<\/em>.<\/p>\n\nWay B: File on your LibreChat server<\/h2>\n
https:\/\/<your-server>\/.well-known\/libretto.json<\/code><\/pre>\n{\n \"version\": 1,\n \"speech\": { \"allowedEngines\": [\"system\"] }\n}<\/code><\/pre>\n\n
location = \/.well-known\/libretto.json {\n default_type application\/json;\n add_header Cache-Control \"no-store\";\n return 200 '{\"version\":1,\"speech\":{\"allowedEngines\":[\"system\"]}}';\n}<\/code><\/pre>\nAlias \/.well-known\/libretto.json \/var\/www\/libretto.json\n<Files \"libretto.json\">\n ForceType application\/json\n<\/Files><\/code><\/pre>\n\nHow to check the effect<\/h2>\n
\n
Limits<\/h2>\n
\n
Contact<\/h2>\n
\nLicenses and quotes: sales@computeq.de<\/a><\/p>\n