This page is machine-translated from French. Read the French original.

Images, videos and voices

Beyond text, WivenLLM can produce images and short videos, read answers aloud, and transcribe speech. These functions are optional : they only exist if an administrator has configured them.

Image generation

Use

In a conversation:

/image un plan de coupe schématique d'une pompe à chaleur, style technique

The image appears in the conversation and can be downloaded. An agent can also generate an image during a task, if the corresponding skill is enabled.

Configuration — administrator

Réglages → Génération d'images. Two types of suppliers:

Local — The models run on your machine; no data is sent out. This requires suitable hardware, in practice a graphics card. Supported local installations include both an integrated engine managed by WivenLLM and image generation servers that you already use.

External — The main commercial image generation services are supported. Your descriptions are then sent to the chosen provider.

Good to know

• The generated images are attached to the conversation.
• Describe the style as much as the subject: "technical diagram in black and white, white background" gives a very different result from "illustration".
• An image generation model cannot reliably write readable text; do not expect visuals with accurate labels.

Video generation

Same principle, with the command /video.

/video une vue aérienne lente d'un chantier de construction, 5 secondes

Realistic expectations: These are short sequences of a few seconds. Generation is long — from several minutes to much longer depending on the supplier and the equipment — and much more demanding than the image.

The configuration is done in Réglages → Génération de vidéos, with the same choice between local execution and external service.

Listen to the responses (text-to-speech)

A play button appears under each answer.

Available options:

• Navigator's voice (by default) — uses the system's built-in text-to-speech function. No configuration required, no data sent anywhere, quality varies depending on the operating system.
• High-quality local voice — a downloaded engine that runs in the browser, more natural than system voice, still without network output.
• External services — the main speech synthesis providers are supported for superior quality; the text of the responses is then transmitted to the provider.

Configuration in Réglages → Préférences audio.

Dictating messages (voice recognition)

A microphone button in the input area transcribes your speech into text. By default, the browser's speech recognition is used.

Important confidentiality point to be aware of: Browser-integrated speech recognition typically transmits audio to the browser publisher's servers. On a system requiring a purely local environment, this is a data output that shouldn't be overlooked—check the behavior of your browser, or disable the feature.

Transcription of audio and video files

Distinct from dictation: when an audio or video file is imported as a document, it is transcribed then indexed like any other text.

The built-in transcription engine is working locally, without a key or network output. An external service can be substituted for it in Réglages → Préférences de transcription.

Common uses: Recordings of meetings, interviews, training sessions, voice messages. The transcript becomes searchable like an ordinary document — "what was decided about the budget at the meeting on the 12th?".

To record a meeting directly from the application and obtain a structured summary, see Meetings.

Quality : It depends on the clarity of the recording, the number of speakers, and any overlap in speech. A meeting recording captured by a laptop microphone will produce inconsistent results.

What comes out of the network