An AI production assistant that works with your Ableton Live.
What it does · Getting started · Connections · Safety · Privacy
Live Smith helps you understand, arrange, and edit a Live Set through conversation. Select a track, Clip, device, or another supported Live object and choose Ask Live Smith. Your conversation starts with that musical context.
Note
Live Smith is beta software and requires an Ableton Live build with Extensions support. See the development guide for installation from source.
- Work with your Set. Inspect tracks, Clips, devices, and MIDI notes, then create or edit MIDI parts, organize tracks and Scenes, adjust mixer settings, and work with observed samples and native Live devices. Analyze isolated Arrangement audio ranges for level measurements.
- Keep conversations organized. Use separate Sessions for different parts of your Set, revisit their history, or collapse the Sessions panel for more space.
- Choose models in the composer. Save several models in one connection Profile, then switch models and supported reasoning levels below the message box. The context meter shows reported usage when available.
- Guide the musical approach. Enable arrangement Skills per Session or mention one for a single request. Open a built-in Skill to read its instructions before enabling it.
- Bring reference material. Paste or drag images, documents, or audio into the composer. You can also attach a selected Live audio source. Input support depends on the model and connection.
- Keep work moving. Queue a follow-up for the next turn, steer the response already in progress, or stop it.
- Search when needed. Compatible Direct API connections can enable hosted Web Search, with search activity and citations visible in the conversation.
Try requests such as:
“Create a four-bar bass MIDI idea on this track.”
“Help the chorus stand out using the parts already in this Set.”
“Inspect this device and explain what its current settings are doing.”
- Install and run the extension using the development guide.
- In Live, right-click a supported object and choose Ask Live Smith.
- Open Settings, create a named Profile, and choose a connection.
- Use Load Models, choose a default model, and Save & Use the Profile. Direct API connections also allow entering a model ID manually.
- Ask for help. Review proposed edits according to the Session’s approval mode.
A Profile groups one connection and its model settings. Once it is saved, the composer lets you change the active Session’s model without returning to Settings.
See model settings for catalog loading, generation options, and capability indicators.
Connect an OpenAI, Anthropic, or compatible API service using its endpoint and API key. Supported request formats are OpenAI Responses, OpenAI Chat Completions, and Anthropic Messages. API usage is billed by the provider.
Hosted Web Search is available through supported OpenAI Responses and Anthropic Messages connections. It is off by default and configured per model.
Sign in through an isolated official Codex CLI connection to use an eligible ChatGPT account’s Codex allowance. It requires a supported Codex CLI installation and does not use or change your normal Codex login.
This connection does not fall back to API-key billing. Hosted Web Search and workspace-managed accounts are not supported by this experimental integration. Claude subscription login is not supported; use an Anthropic API connection instead.
See model connections for setup requirements and provider-specific limitations.
Each Session has an approval mode:
- Manual asks before every proposed edit plan.
- Low Risk applies lower-risk plans automatically and asks before protected actions such as deletes, Clip writes, and sample replacements.
- Accept Everything automatically approves all validated plans, including deletes and replacement writes.
All modes still inspect the relevant Live state, validate actions, and check that the Set has not changed before applying an edit. One approved plan may create more than one Live Undo step.
Live Smith does not run arbitrary model-generated code. It does not inspect or edit Automation, browse installed presets, or load a VST by plug-in identifier. Existing devices can be inspected and edited where Live exposes their parameters.
Sessions keep conversation and action history with their Live context. Previous Sessions can be restored explicitly; matching names alone do not make an old conversation the same Live object.
Skills provide musical workflow guidance. Three built-ins cover section
energy, musical variation, and instrument roles. They start disabled; View
opens the full instructions without enabling them. You can import a local
SKILL.md, enable up to four Skills
per Session, or use $skill-id for one request.
Skills do not grant additional permissions or tools.
Attachments support PNG, JPEG, WebP, PDF, DOCX, XLSX, PPTX, WAV, and MP3. Office documents are read as text. Image, native PDF, and audio use depends on the selected model and connection; attaching a file does not guarantee it can be sent to every model. Use paste or drag-and-drop rather than a system file picker.
Queue and Steer are configured under Settings → Conversation Behavior. Queued follow-ups belong to the open window; Live Smith warns before closing with pending work.
Profiles, Sessions, attachments, and imported Skills are stored locally. Prompts, relevant Live context, selected Skill guidance, and supported attachment content are sent to the model provider you choose.
Direct API keys are stored in local Profile settings as plain text. The subscription connection keeps its login in a separate local Codex home. Do not commit, share, or cloud-sync either storage location.
- Development guide: prerequisites, local setup, validation, packaging, and development data.
- Model connections: connection requirements, model settings, capability evidence, and protocol limits.
- Architecture: module responsibilities, data flow, and safety boundaries.
- Contributor guide: working conventions and required checks.
- Third-party notices.