New features:
- Scheduled agents: run agents on a repeating timer using CRON-like syntax, for example every day at 8am
- Send Voice as Audio: send your voice recording to audio-capable models instead of just the transcript, and play it back in chat
- Long-term memory in group chats: each character remembers the scene and recalls from it on their own turns
- Barge-in for voice chat: interrupt Layla by saying "stop", "wait", or "hang on"
- Press-and-hold push-to-talk: hold the voice button to talk, release to send
- MiniCPM-V 4.7 support, including image understanding
- Codex Login: use your ChatGPT subscription with Layla instead of API credits
- Skills in character workspaces: import skills for a character to use in its own workspace
- Preserve Thinking: compatible models can refer back to their reasoning from earlier replies
- Scrollable code blocks, tables, and maths, with a wrap toggle for code

Improvements:
- Asking a character for a picture now shows an image offer you can accept or decline
- New default characters that demonstrate Layla features, each with a bundle of agents
- Adjust sampler settings like temperature and top-p mid-chat from Chat Info
- Redesigned chat history, group chat, and the Transcription mini-app
- Redesigned setup screen for iPad
- The Layla Cloud model picker now shows your login status and subscription plan
- Progress is shown while loading a model and while installing or removing mini-apps

Bug fixes:
- Fixed delayed microphone startup in voice chat and missing microphone permission support
- Fixed downloaded voices and vision models failing to load after an update or backup restore
- Fixed downloads being marked complete before their files were ready
- Fixed earlier thinking and agent calls appearing as chat text after selecting a regenerated reply
- Fixed the status tracker not being saved to long-term memory
- Fixed group chats sending images to characters whose model can't read them
- Fixed scene lorebooks not loading the first time a group chat was opened
- Fixed web automation getting stuck on sites with a verification challenge

- Fixed a bug where some agents showed errors when starting a chat.
- Fixed a bug where the file picker did not appear after pressing Import Data on iOS.

- Fixed some functions hanging during background execution in task.js.
- Fixed a small OpenCL GPU performance regression.

Layla 7.5.0 is the full public release of the 7.5 line.

NEW

- Character workspaces: give each character a dedicated private workspace - a filesystem its agents can read, write, update, and delete files in. Attach the Character Workspace and Workspace Shell agents to enable it, and manage files from the Create Character screen or Chat Info, including importing files and ZIP bundles and downloading a backup.
- Filesystem-based memory: characters can keep files like system_prompt.md, Memory.MD, and Soul.MD in their workspace. The agent reads system-prompt files at the start of a conversation to guide what it reads and updates.
- Automatic agent triggering: enabled agents are added to the system prompt and the model decides when to activate them, instead of relying on trigger phrases. Layla also handles models that call two or more tools in one turn.
- Slash commands for agents: type / in the message field to list the agents available to a character, then pick one to trigger it directly.
- Layla Music: a new mini-app for the music you generate. Browse the latest releases from other users, generate music, collect tracks into albums, set cover art, create artists, and import your own audio.
- Experimental Streaming MoE: run mixture-of-experts models larger than your device's RAM by streaming expert weights from storage.
- Partial and complete backups: back up and restore individual sections, and optionally include custom mini-apps, model files, and inference engines.
- Apple App Intents (experimental): Layla now exposes App Intents so Siri shortcuts can trigger Layla as part of a shortcut. This is an early implementation and is expected to change.
- Layla SDK v7.5: the OpenAI-compatible endpoint now supports tool calls, with new notification-scheduling and Layla Cloud login APIs for mini-apps.

IMPROVED

- Layla now uses the chat template built into each model, so there is no need to set a system prompt format per model. Existing system prompts still work.
- Multiple images can now be attached to a single message.
- SillyTavern Presets support regexes and older preset formats from before SillyTavern 1.10.
- The MCP Support mini-app adds automatic server detection and searchable, filterable tool lists.
- The References mini-app no longer requires Long-term memory, and uses it to improve document ingestion when installed.
- The ElevenLabs integration now uses their newest API and supports multilingual voices.
- Faster loading of the Character Selection page for large character libraries.
- Pagination now accepts a page number instead of stepping one page at a time.

FIXED

- Fixed backups becoming corrupted if the app was closed too soon after starting one.
- Fixed some models failing to handle a greeting or assistant message as the first message.
- Fixed message regeneration not working.
- Fixed max_response_length = 0 not being respected.
- Fixed image-generation context no longer working.
- Fixed animated images (WebP, APNG) losing frames when cropped.
- Fixed exporting an LLM not keeping its file extension.
- Fixed Python error handling on iOS.

- fixed a crash after music generation