← MAP AudioCONTENT HISTORY

Update to MAP Audio

Snapshot Oct 28, 2026 · 13:06 UTC · version 0.4.0

Collection source: downloaded plugin package.

WHAT CHANGED

Instructions updated for map-audio

Full description — Now says: Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, loop and annotate its timeline, process it through an MFX effect...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save MAP Audio and check future changes in Following.

Up to 10 plugins free · no card required.

All fields and original values.

Full description

Before

Oct 26, 2026 · 18:05 UTC

Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, or loop and annotate its timeline with MAP Audio.

After

Oct 28, 2026 · 13:06 UTC

Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, loop and annotate its timeline, process it through an MFX effect preset, or open PAM, MAP Audio's sampler and sequencer, to play and change a be...

Skill instructions

Before

Oct 26, 2026 · 18:05 UTC

or loop and annotate its timeline with MAP Audio. tool; audio bytes should not be placed in conversation text. The hosted workspace provides inspection, not sound generation or desktop processing. It does not support accounts, checkout, ...

After

Oct 28, 2026 · 13:06 UTC

loop and annotate its timeline, process it through an MFX effect preset, or open PAM, MAP Audio's sampler and sequencer, to play and change a beat in the conversation. ## Recordings tool; audio bytes should not be placed in conversation ...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,29 +1,64 @@
 ---
 name: map-audio
-description: Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, or loop and annotate its timeline with MAP Audio.
+description: Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, loop and annotate its timeline, process it through an MFX effect preset, or open PAM, MAP Audio's sampler and sequencer, to play and change a beat in the conversation.
 ---
 
 # MAP Audio
 
+## Recordings
+
 Use `open_audio_workspace` to open the player. Use `open_demo_audio` when the user
 wants to try the supplied synthetic example without attaching a recording. For a recording attached by the user,
 call `display_audio_file` with the host-provided file object. Reuse the returned
 `audioId` for later playback, region and annotation changes. Never invent a download
 URL, file ID, audio ID or server path. `read_audio_chunk` is an app-only byte-transfer
-tool; audio bytes should not be placed in conversation text.
+tool; audio bytes should not be placed in conversation text. ChatGPT's desktop app calls
+`view_audio_file` itself when the user opens a WAV, FLAC, MP3 or M4A file in the file viewer;
+do not call it.
 
 The browser publishes measured statistics, playback position, selected regions and
 annotations to the conversation. Use that context when available; wait for analysis
 or say a measurement is unavailable instead of inventing values. Measurements and
 waveforms do not establish that you listened to a recording.
 
-The hosted workspace provides inspection, not sound generation or desktop
-processing. It does not support accounts, checkout, activation or model downloads.
-If a user requests those operations, explain the available scope without upgrade
-prompts. Do not call tools that the connected server does not expose.
+## PAM
+
+Use `open_pam` when the user wants to make or hear a beat, or to try PAM. When they
+name a style, mood or tempo, call `list_pam_presets` first and pass the closest preset's
+slug; `open_pam` also takes a variation from 1 to 8 (with a preset) and a tempo in BPM. A new PAM
+starts silent: tell the user to press Play inside PAM. The widget reports the loaded preset,
+tempo, variation and whether PAM is playing. Describe only what it reports.
+
+When `open_pam` returns a `pamId`, the control tools act on that PAM: `get_transport`,
+`start_transport`, `stop_transport`, `full_stop_transport`, `set_bpm`, `load_variation`,
+`cancel_queued_variation`, `randomize` and `load_preset`. Pass the `pamId` of the PAM the user
+means. `start_transport` works only after the user has pressed Play inside that PAM once.
+
+PAM in ChatGPT runs its browser engine with MAP Audio's presets. It cannot load the
+user's own samples, save presets, export audio or control the desktop plugin. Calling
+`open_pam` again opens a second PAM; when one starts playing, the others pause.
+
+## MFX
+
+Use `apply_mfx_preset` when the user wants a recording processed with effects (a vocal chain, drum bus,
+reverb, distortion, a mix-bus treatment) and does not need MFX itself open. Call `list_mfx_presets` first,
+narrowed with a `category` or `query` from the request, and pass the closest preset's slug, with the
+attachment or an `audioId`; a variation from 1 to 8 and a tempo for synced effects are optional. Recordings
+up to 32 MiB and five minutes (about three minutes of WAV). The widget renders the audio, lets the user compare it with the original and download
+it, and reports the processed copy's own `audioId`: pass that to `display_audio_file` to show its loudness.
+Until the widget reports it, the processing has not finished; describe only what it reports.
+
+## Scope
+
+Every tool needs the user's MAP Audio account, which ChatGPT asks them to connect. Controlling
+PAM from ChatGPT comes with a PAM licence on that account; without one, `open_pam` returns
+`control: "not_included"` and the control tools say so. Then the user can still play PAM by hand.
+Processing with `apply_mfx_preset` comes with an MFX licence the same way; listing MFX presets does not.
+State that plainly and give the link the tool returns; do not mention prices, plans, discounts or
+upgrades, and do not offer to buy anything. MAP Audio does not generate sound with AI and has no
+checkout, activation or model downloads here. Do not call tools that the connected server does not expose.
 
 Audio IDs and download links are private capabilities and expire after one hour.
 Keep them in this conversation. Ask for a fresh attachment when a file expires.
-Direct support questions to https://map.audio/contact and privacy questions to the
-workspace privacy page. MAP Audio is the publisher; this workspace is not the PAM
-or MFX desktop plugin.
+Direct support questions to https://map.audio/contact and privacy questions to
+https://audio.map.audio/privacy.
Full technical diff · 2 changed fields

changed /description

BEFORE
"Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, or loop and annotate its timeline with MAP Audio."
AFTER
"Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, loop and annotate its timeline, process it through an MFX effect preset, or open PAM, MAP Audio's sampler and sequencer, to play and change a beat in the conversation."

changed /skill_md_contents

BEFORE
"---\nname: map-audio\ndescription: Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, or loop and annotate its timeline with MAP Audio.\n---\n\n# MAP Audio\n\nUse `open_audio_workspace` to open the player. Use `open_demo_audio` when the user\nwants to try the supplied synthetic example without attaching a recording. For a recording attached by the user,\ncall `display_audio_file` with the host-provided file object. Reuse the returned\n`audioId` for later playback, region and annotation changes. Never invent a download\nURL, file ID, audio ID or server path. `read_audio_chunk` is an app-only byte-transfer\ntool; audio bytes should not be placed in conversation text.\n\nThe browser publishes measured statistics, playback position, selected regions and\nannotations to the conversation. Use that context when available; wait for analysis\nor say a measurement is unavailable instead of inventing values. Measurements and\nwaveforms do not establish that you listened to a recording.\n\nThe hosted workspace provides inspection, not sound generation or desktop\nprocessing. It does not support accounts, checkout, activation or model downloads.\nIf a user requests those operations, explain the available scope without upgrade\nprompts. Do not call tools that the connected server does not expose.\n\nAudio IDs and download links are private capabilities and expire after one hour.\nKeep them in this conversation. Ask for a fresh attachment when a file expires.\nDirect support questions to https://map.audio/contact and privacy questions to the\nworkspace privacy page. MAP Audio is the publisher; this workspace is not the PAM\nor MFX desktop plugin.\n"
AFTER
"---\nname: map-audio\ndescription: Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, loop and annotate its timeline, process it through an MFX effect preset, or open PAM, MAP Audio's sampler and sequencer, to play and change a beat in the conversation.\n---\n\n# MAP Audio\n\n## Recordings\n\nUse `open_audio_workspace` to open the player. Use `open_demo_audio` when the user\nwants to try the supplied synthetic example without attaching a recording. For a recording attached by the user,\ncall `display_audio_file` with the host-provided file object. Reuse the returned\n`audioId` for later playback, region and annotation changes. Never invent a download\nURL, file ID, audio ID or server path. `read_audio_chunk` is an app-only byte-transfer\ntool; audio bytes should not be placed in conversation text. ChatGPT's desktop app calls\n`view_audio_file` itself when the user opens a WAV, FLAC, MP3 or M4A file in the file viewer;\ndo not call it.\n\nThe browser publishes measured statistics, playback position, selected regions and\nannotations to the conversation. Use that context when available; wait for analysis\nor say a measurement is unavailable instead of inventing values. Measurements and\nwaveforms do not establish that you listened to a recording.\n\n## PAM\n\nUse `open_pam` when the user wants to make or hear a beat, or to try PAM. When they\nname a style, mood or tempo, call `list_pam_presets` first and pass the closest preset's\nslug; `open_pam` also takes a variation from 1 to 8 (with a preset) and a tempo in BPM. A new PAM\nstarts silent: tell the user to press Play inside PAM. The widget reports the loaded preset,\ntempo, variation and whether PAM is playing. Describe only what it reports.\n\nWhen `open_pam` returns a `pamId`, the control tools act on that PAM: `get_transport`,\n`start_transport`, `stop_transport`, `full_stop_transport`, `set_bpm`, `load_variation`,\n`cancel_queued_variation`, `randomize` and `load_preset`. Pass the `pamId` of the PAM the user\nmeans. `start_transport` works only after the user has pressed Play inside that PAM once.\n\nPAM in ChatGPT runs its browser engine with MAP Audio's presets. It cannot load the\nuser's own samples, save presets, export audio or control the desktop plugin. Calling\n`open_pam` again opens a second PAM; when one starts playing, the others pause.\n\n## MFX\n\nUse `apply_mfx_preset` when the user wants a recording processed with effects (a vocal chain, drum bus,\nreverb, distortion, a mix-bus treatment) and does not need MFX itself open. Call `list_mfx_presets` first,\nnarrowed with a `category` or `query` from the request, and pass the closest preset's slug, with the\nattachment or an `audioId`; a variation from 1 to 8 and a tempo for synced effects are optional. Recordings\nup to 32 MiB and five minutes (about three minutes of WAV). The widget renders the audio, lets the user compare it with the original and download\nit, and reports the processed copy's own `audioId`: pass that to `display_audio_file` to show its loudness.\nUntil the widget reports it, the processing has not finished; describe only what it reports.\n\n## Scope\n\nEvery tool needs the user's MAP Audio account, which ChatGPT asks them to connect. Controlling\nPAM from ChatGPT comes with a PAM licence on that account; without one, `open_pam` returns\n`control: \"not_included\"` and the control tools say so. Then the user can still play PAM by hand.\nProcessing with `apply_mfx_preset` comes with an MFX licence the same way; listing MFX presets does not.\nState that plainly and give the link the tool returns; do not mention prices, plans, discounts or\nupgrades, and do not offer to buy anything. MAP Audio does not generate sound with AI and has no\ncheckout, activation or model downloads here. Do not call tools that the connected server does not expose.\n\nAudio IDs and download links are private capabilities and expire after one hour.\nKeep them in this conversation. Ask for a fresh attachment when a file expires.\nDirect support questions to https://map.audio/contact and privacy questions to\nhttps://audio.map.audio/privacy.\n"
Full snapshot data
{
  "description": "Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, loop and annotate its timeline, process it through an MFX effect preset, or open PAM, MAP Audio's sampler and sequencer, to play and change a beat in the conversation.",
  "included_files": [],
  "name": "map-audio",
  "skill_md_contents": "---\nname: map-audio\ndescription: Play an attached recording, inspect its waveform, spectrogram and browser-measured loudness, loop and annotate its timeline, process it through an MFX effect preset, or open PAM, MAP Audio's sampler and sequencer, to play and change a beat in the conversation.\n---\n\n# MAP Audio\n\n## Recordings\n\nUse `open_audio_workspace` to open the player. Use `open_demo_audio` when the user\nwants to try the supplied synthetic example without attaching a recording. For a recording attached by the user,\ncall `display_audio_file` with the host-provided file object. Reuse the returned\n`audioId` for later playback, region and annotation changes. Never invent a download\nURL, file ID, audio ID or server path. `read_audio_chunk` is an app-only byte-transfer\ntool; audio bytes should not be placed in conversation text. ChatGPT's desktop app calls\n`view_audio_file` itself when the user opens a WAV, FLAC, MP3 or M4A file in the file viewer;\ndo not call it.\n\nThe browser publishes measured statistics, playback position, selected regions and\nannotations to the conversation. Use that context when available; wait for analysis\nor say a measurement is unavailable instead of inventing values. Measurements and\nwaveforms do not establish that you listened to a recording.\n\n## PAM\n\nUse `open_pam` when the user wants to make or hear a beat, or to try PAM. When they\nname a style, mood or tempo, call `list_pam_presets` first and pass the closest preset's\nslug; `open_pam` also takes a variation from 1 to 8 (with a preset) and a tempo in BPM. A new PAM\nstarts silent: tell the user to press Play inside PAM. The widget reports the loaded preset,\ntempo, variation and whether PAM is playing. Describe only what it reports.\n\nWhen `open_pam` returns a `pamId`, the control tools act on that PAM: `get_transport`,\n`start_transport`, `stop_transport`, `full_stop_transport`, `set_bpm`, `load_variation`,\n`cancel_queued_variation`, `randomize` and `load_preset`. Pass the `pamId` of the PAM the user\nmeans. `start_transport` works only after the user has pressed Play inside that PAM once.\n\nPAM in ChatGPT runs its browser engine with MAP Audio's presets. It cannot load the\nuser's own samples, save presets, export audio or control the desktop plugin. Calling\n`open_pam` again opens a second PAM; when one starts playing, the others pause.\n\n## MFX\n\nUse `apply_mfx_preset` when the user wants a recording processed with effects (a vocal chain, drum bus,\nreverb, distortion, a mix-bus treatment) and does not need MFX itself open. Call `list_mfx_presets` first,\nnarrowed with a `category` or `query` from the request, and pass the closest preset's slug, with the\nattachment or an `audioId`; a variation from 1 to 8 and a tempo for synced effects are optional. Recordings\nup to 32 MiB and five minutes (about three minutes of WAV). The widget renders the audio, lets the user compare it with the original and download\nit, and reports the processed copy's own `audioId`: pass that to `display_audio_file` to show its loudness.\nUntil the widget reports it, the processing has not finished; describe only what it reports.\n\n## Scope\n\nEvery tool needs the user's MAP Audio account, which ChatGPT asks them to connect. Controlling\nPAM from ChatGPT comes with a PAM licence on that account; without one, `open_pam` returns\n`control: \"not_included\"` and the control tools say so. Then the user can still play PAM by hand.\nProcessing with `apply_mfx_preset` comes with an MFX licence the same way; listing MFX presets does not.\nState that plainly and give the link the tool returns; do not mention prices, plans, discounts or\nupgrades, and do not offer to buy anything. MAP Audio does not generate sound with AI and has no\ncheckout, activation or model downloads here. Do not call tools that the connected server does not expose.\n\nAudio IDs and download links are private capabilities and expire after one hour.\nKeep them in this conversation. Ask for a fresh attachment when a file expires.\nDirect support questions to https://map.audio/contact and privacy questions to\nhttps://audio.map.audio/privacy.\n"
}

SHA-256 of public snapshot: 3fa389ad28809aff8bd52e042c3e31d545657cbcdb58c4a1b06c8ff2ae29902f