Images and Voice
Narrova accepts visual reference, creates new story images, and turns microphone input into editable text. These tools help when an image or spoken thought communicates creative intent faster than a long typed prompt.
Attach an image
Location: Narrova → conversation composer → Plus → Add files and images.
Action: Choose an image and complete the upload.
Outcome: The image is added to Conversation Context for the current thread. If documents are selected at the same time, those documents may also be sent to one additional Story or Storyform Context.
Validation: The image appears in the composer attachment row before you send and remains attached to the submitted message afterward.
Images are conversation-scoped. Use them for a temporary visual reference, comparison, page, sketch, or design direction. Use Story or Storyform document managers for durable text sources and comic-processing workflows.
Generate an image
Ask directly for the visual you want: an image, poster, cover, headshot, portrait, concept, diagram, or other artwork. Include the subject, purpose, composition, era, setting, and visual tone that matter to the result.
Location: Narrova → conversation.
Action: Send an explicit request such as, “Create a vertical story poster for this Storyform using the Visual Design Overview.”
Outcome: Narrova shows generation progress, then places the completed image in the response. Storyform-scoped results can also appear in the Storyform Image Gallery.
Validation: Open the final image at full size and use its download action. If the result is blank or generation fails, revise the request with a more concrete visual subject and try again.
The Generate Story Poster Skill creates a cinematic one-sheet from Story or Storyform Context. Player headshots use the Player portrait manager so the accepted image stays attached to the correct Player; Story poster requests compose the available Story identity and visual context into one cover image.
Dictate a request
Location: Narrova → conversation composer → microphone.
Action: Allow microphone access, speak, then choose the stop control to transcribe or the primary checkmark to stop and submit.
Outcome: Narrova converts the recording into text. You can review the transcription before sending unless you chose stop and submit.
Validation: Confirm the spoken words appear in the composer or as the submitted request. If the browser reports no speech or blocks microphone access, continue by typing and review the site's microphone permission.
The moving level indicator confirms that the browser is receiving audio. Recording stops when you finish, and Narrova releases the microphone after transcription.
Common mistakes
Saying “do it” after a visual discussion. Ask explicitly to create or generate the image so Narrova can distinguish a visual request from a request for more text.
Treating an image attachment like durable Story Context. Images stay in Conversation Context. Put reusable textual canon in the Story or Storyform document manager.
Submitting before checking the transcript. Names and Dramatica terms can be misheard. Review the text when exact terminology matters.
Writing use: Attach a visual reference, dictate the emotional and structural goal, then ask Narrova to generate one concrete image that expresses that specific intent.