What's new in Novelcrafter

New Help & Profile Menu updates

To make things simpler, we’ve redesigned the Profile menu, and moved out the help section into its own little button:

1. The profile menu now has quick links to the settings - no more clicking around
2. The help menu also shows a live service status - in case you want to see if e.g. Anthropic is down.

New AliPay option

For people in China, our payment provider recently added the ability to pay via AliPay! You’ll need update your existing payment method in the billing portal, if you want to switch over.

AI & Prompting

• Added native integration with Arli AI (another fixed-subscription-price AI vendor)
• Fixed empty spaces in API keys not being removed and causing confusion when no models show up
• Fixed archived codex entries being accidentally included in the AI context

Other changes

• Added a retry button to all sync error messages. This should help with saving when unknown errors occur
• When importing a novel, any save errors will now be shown to the user
• Fixed exported files using UTC time in the file name, and not the computer’s local time
• Fixed clearing out scene contents when it just had an empty beat/section/etc.
• Fixed codex entries with just punctuation in their name crashing the app
• Various other bug fixes and improvements

Bit of a small one today, but we wanted to fix the latency issues introduced last week!

Custom prompting

• When sending codex data to the AI, the entries are now sorted alphabetically (for those that split up their codex entries: this should help quite a bit!)
• Added new “names” format to codex functions, which skips all descriptions (useful for dictation prompts), for example : codex.all("names") or codex.getAllByType("character", "names")
• Added new “system as user” toggle for models that don’t support system messages (for o1 and some infermatic models)
• Added an option to disable streaming for models that don’t support those kinds of responses (o1 for example)

Other changes

• Fixed floating panels (codex, snippet, chat) appearing in front of (alert) modals
• Fixed highlighting markers in timeline not showing their actual height
• Fixed collapsed sections still showing highlighting markers in timeline
• Some other bugfixes and improvements

For this Halloween, the spirits have haunted us and made us do something we’ve never done before!

We’ve reset trials - and extended them, too!

You heard right: Everyone still in a trial, or who had a taste before November 1st, got a reset - and we permanently extended them by a week. Which means everyone has until November 21st to try out Novelcrafter (again).

Some are hobbyists who only write on weekends, others have family obligations; we know everybody’s time is precious. With November being arguably the most popular month for writing, we decided to give everyone the time they need to explore Novelcrafter.

Big thanks to all the people who have given their feedback and filled out the trial survey so far (and continue to do so)!

November’s Monthly Muse: Tarot Tales

If you want to be visited by the spirits as well, why not try out this month’s game of Tarot cards to inspire your next story?

Shuffle the deck and draw cards for the Hero(ine)'s Journey, your character arc, or for world building inspiration. The writing prompt is hidden in the details. Will you find a tale of love and loss or perhaps a twist of fate?

Check out Tarot Tales here

Other changes

• Added word count per chapter in review mode
• Allow sections to be excluded from word counting
• Added undo/redo buttons to editor bubble menu
• Added rotate/zoom/flip controls to image uploader
• Fixed an issue with nested modals on mobile
• Fixed codex/snippet/chat search being cleared when moving between plan/write/… modes
• Various other bug fixes and improvements

Updated Word Counting… again

We’ve updated the word counting system when you’re using an up-to-date browser. This means that we now support a much wider array of languages, since the actual counting is provided by your system itself. If you’re on an older browser (e.g. Firefox Version older than 125), please update accordingly to make use of the new version.

While we tested this with our existing changes we did on September 5, please report any errors you might find with your language!

Improved image upload quality

On certain images (e.g. ones with glitter, line art, or harsh angles) the image uploads (especially covers) were not as pretty as they can be - we updated the internals to get rid of any (pixelated) artifacts, but any previously uploaded images have to be re-uploaded if you want to take advantage of the new quality.

Other changes

• Added native integration for OpenPipe for those that want to use their fine-tuning services
• Fixed the Mistral integration not being able to load the model list
• Fixed being unable to export snippets that had text copied from AI generations
• Other various fixes and improvements

Today’s update is a patch release for things that cropped up with all the editor updates:

• Added support for lists in scene beats and codex additions.
• Fixed codex addition formatting not showing up properly in Codex Details or the Matrix view. All your bold, highlighted or numbered contents now show up as well.
• Fixed colored/highlighted text in manuscript not matching up with the marker timeline to the right
• Fixed issues with Grammarly not working properly after the editor updates
• Fixed some actions being ignored on some touch devices
• Fixed a couple overflow issues where style menus could be cut off

Other changes

• Added support for exporting individual snippets
• Various other fixes and improvements

More rich text formatting options

Have you ever got a nice response in Chat, then saved it as a snippet and discovered all the pretty formatting has been lost? Yeah, we, too - too many times.

With today’s update we added proper support for lists (numbered and bullets), headings (H1 to H3) and other formatting options to (almost) all text editors:

• codex descriptions and notes
• manuscript/write view
• your chat questions/messages
• snippets

Take note that the Word export does not support all the features yet (we’re still working on those)

AI / Prompting

For people who want to spend a monthly price, instead of credits, we now added native support for Featherless AI and Infermatic. They mainly host NSFW-friendly models, so these are a good alternative if you’re writing romance stories.

• Added native connection to Featherless AI
• Added native connection to Infermatic
• Added hostname/IP/HTTPs options to LM Studio integration. This should help when you’re connecting via the network
• We’re now filtering out any voice or image models from Open AI, as we don’t support those within Novelcrafter
• Fixed context calculations for Gemini models (OpenRouter changed their calculations, so using these models should be cheaper now)
• Changed the Cohere Command-R+ models on system prompts to use the older April version. Internal testing has shown that it’s a bit more creative than the August version.
• Added a “copy” button next to prompt messages for easy access

Chat

We also added a setting to change chat message flow for threads: You can either have messages start at the top, or bottom, which should help with when you want to read the answer as soon as it comes in, without having to wait until it stops scrolling.

Furthermore, the extraction feature now supports tags/labels as well, if you add them via square brackets to the name, like the following format: First name "Alias" Last name [Tag A, Tag B].

Other changes

• Added an option to also clone snippets when using a novel as a template
• The appearances tab in the codex will now show better titles for chat (unnamed threads will use the first message as fallback, just how the sidebar does it)
• You can now upload a novel cover from your clipboard as well
• Various other bug fixes and improvements

This release updates the system prompt model lists with the following additions and changes:

1. Added more free models like Gemma 2, Llama 3.1 and the like
2. Added L3.1 Euryale 70b as a more affordable NSFW option
3. Moved Claude 2.0 from Popular to just the “Anthropic” group

Other changes

• The codex matching now takes apostrophes in plural suffixes into account (e.g. “Peter’s” is now matched in full instead of just “Peter”)
• Chat threads in the codex appearance tab are now sorted in reverse chronological order
• Archived codex entries that are used in POV settings are no longer being shown or added to prompts
• Fixed errors around empty OpenRouter custom routing options

This update includes a couple fixes for when data can’t be saved and reduce data loss on unreliable connections as well as improving detection around logged out users.

1. Sometimes the internet can be intermittent, so we added a way to retry a request when those “failed to fetch” errors happen. This way changes are not lost when they could not be saved on first try.

2. In addition, we added custom error handling for the “Unauthorized” errors; we now give you a warning and an option to reload the page.

3. We also improved the error message for when you are not allowed to change or update something. The system now gives a better help text on why that is.

Full Project and chat exports are here

You can now export your chats just like you can export your codex or snippets! In addition, the novel export screen now has a section to include other aspects of your novel to get a single “full project” export of your novel.

Codex

• Added a new global setting for the codex to always create new entries in the series scope (helpful when most of your entries are part of a bigger universe)
• Fixed support for codex entries with accents or other special characters in the codex search bar (e.g. Élise can now be found via Elise as well).
• Fixed being unable to upload a thumbnail to a series codex entry that you were invited as an editor to.

Write

• Added the ability to show/hide scene beats in read-only novels as well as revision histories.
• Fixed adding an empty paragraph in scenes that only have a blockquote

Chat

• Added a new “split left/right” option to chats so you can turn them into a side panel when you want to work in another view
• Added new “Empty threads” filters to chats. Sometimes you just start a new thread and don’t end up using it. This makes those easier to find.
• Fixed the chat message taking your input focus away when the AI has finished writing. This was annoying when you were editing a codex entry as you were waiting.
• Fixed “Extract” being available in a read-only novel (was kind of useless since you can’t save anything)

Prompts

• Update model filtering to support new OpenAI o1 models
• Updated prompt parsing to keep indentation when calling functions. This means XML indentation should be kept when desired.

Other changes

• You can now subscribe to Novelcrafter anytime throughout your trial (and not just near the end of it)
• Added number of members + shared contents in team settings tabs
• Fixed team lists with more than 25 members not loading all user details at once
• Various other bug fixes and improvements

Word counting changes

This update makes word counting to be more in line with Scrivener. Both, Word and Google Docs (which we have used as a guideline so far) have issues counting words with em-dashes, punctuation and other special characters. The updated word counting is now more like what people would count as real words.

For comparison:

• I wish you would - oh, never mind. now counts as 7 words, not 8.
• It was … complicated. now counts as 3 words, not 4.

Performance improvements

We internally upgraded to a new version of the framework Novelcrafter is using to render stuff on screen. While there were great performance improvements, the memory consumption should be even less for bigger novels now. Though we did extensive testing, as always, please report if some things aren’t updating quite right.

Update to Mistral models in system prompts

For all system prompts, we now configured all Mistral models to go through the “Mistral” provider on OpenRouter. While OpenRouter does allow calls to “Azure” as well, those have a special moderation layer that can cut off the output too early if it detects an issue, causing you to loose money as the AI already started responding. Novelcrafter cannot show you when these “in-stream moderation” errors happen yet, so we opted for this solution for the time being.

Other Changes

• Added the ability to copy all scene beats into the clipboard (for scenes, chapters and acts)
• Added a “Hide my email” setting for YouTubers/presenters/teachers that don’t want to have their personal mail on display.
• Fixed some codex detection issues on older versions of Safari. We’re now using a fallback that should work OK for the most part. If issues still arise, please update your browser.
• Fixed not being able to dissolve collapsible sections
• Fixed chapter titles (and automatic numbering) not always refreshing/updating and being in an inconsistent state
• Fixed a few paragraph indentation inconsistencies with beats/additions and sections
• Fixed some visual shifting when showing a horizontal cursor before a beat at the start of a scene
• Fixed codex thumbnail uploads saving to the wrong entry on slow connections, when immediately switching to another one
• Fixed context.previousBeat always picking first beat of a scene, instead of the one before