AccurateScribe.ai – Transcribe

Use this tool only when the user wants AccurateScribe to process an audio or video source and produce new subtitles/captions, or explicitly asks to open the AccurateScribe subtitle interface. Do not use it to translate, edit, review, summarize, or convert transcript/subtitle text already pasted into the conversation. This tool must open the AccurateScribe subtitle widget; do not ask the user to upload, attach, or send media files in the ChatGPT conversation because chat attachments are not processed by this app. Once the widget is visible, tell the user to choose or drag the media file inside the AccurateScribe widget. If the widget is not visible or cannot be opened, direct the user to https://accuratescribe.ai/transcribe and tell them to upload the file on that page instead. After the widget is open, do not call the file-management tools such as `get-upload-url` or `insert-transcription-record` yourself: the widget uploads the media file, creates the job, and polls the status automatically. Use `get-transcription-result` only when the user asks for the finished subtitle data. If the user needs to upgrade or pay for premium access, direct them to https://accuratescribe.ai/pricing.

subtitle-generator

Use this tool only when the user wants AccurateScribe to process an audio or video source and produce a new transcription, or explicitly asks to open the AccurateScribe transcription interface. Do not use it to translate, edit, review, summarize, or convert transcript/subtitle text already pasted into the conversation. This tool must open the AccurateScribe transcription widget; do not ask the user to upload, attach, or send media files in the ChatGPT conversation because chat attachments are not processed by this app. Once the widget is visible, tell the user to choose or drag the media file inside the AccurateScribe widget. If the widget is not visible or cannot be opened, direct the user to https://accuratescribe.ai/transcribe and tell them to upload the file on that page instead. After the widget is open, do not call the file-management tools such as `get-upload-url` or `insert-transcription-record` yourself: the widget uploads the media file, creates the transcription job, and polls the status automatically. Use `get-transcription-result` only when the user asks for the finished transcript or subtitle data. If the user needs to upgrade or pay for premium access, direct them to https://accuratescribe.ai/pricing.

transcribe

Creates or retrieves a shareable URL for a transcription. The response returns the share URL needed by the user and does not expose internal share tokens, personal identifiers, session data, telemetry, or debugging fields.

share-transcription

Creates a new transcription record for a file that has already been uploaded or for a supported media URL, and stores metadata such as filename, language selection, diarization options, and duration. For uploaded files, the server derives and validates the storage object before starting or tracking the transcription job.

insert-transcription-record

Deletes a transcription record for a specific fileId, or deletes all transcription records for the current user if deleteAll is set. This is a destructive operation and can permanently remove access to the stored transcription record.

delete-transcription

Generates a presigned upload URL for an audio/video file and returns only the upload data needed for the next step, such as fileId and upload URLs. It does not return storage paths, personal identifiers, session data, telemetry, or internal debugging fields.

get-upload-url

Checks the transcription status for a user-owned AccurateScribe record and returns the latest user-facing result when completed, such as transcript text, summary, normalized subtitle entries, language, and duration. For subtitle translation or any task that must preserve cue timestamps, use subtitleEntries when it is non-empty. Use this tool only when the user asks to retrieve an AccurateScribe transcription and a valid fileId is already known or was selected from get-filelist; when chaining from get-filelist, pass the selected record's id as fileId. Do not use it for pasted transcript/SRT text, example JSON, generic translation, or subtitle-format conversion. If the user needs to view the complete transcription content, direct them to https://accuratescribe.ai/transcribe on AccurateScribe.ai, where full content may require a subscription. If the user needs to upgrade or pay for premium access, direct them to https://accuratescribe.ai/pricing. It does not return personal identifiers, session data, telemetry, or internal debugging fields.

get-transcription-result

Retrieves user preferences and coarse account entitlement needed by the widget, limited to UI language and a hasPremiumAccess boolean. It does not return payment status, subscription status, personal identifiers, session data, telemetry, or internal debugging fields.

get-user-preferences

Retrieves one page of the user's AccurateScribe transcription history. To load older records, pass the last returned record's created_at as cursor.createdAt and id as cursor.id. For polling, pass fileIds to refresh only those user-owned records; do not combine fileIds and cursor. Use it only for the user's AccurateScribe transcription history, not for files on the user's computer, Downloads folder, cloud drive, or generic file management. When a selected record is passed to get-transcription-result, map the record's id field to that tool's fileId input. The response is limited to user-facing file fields needed by the widget and does not include personal identifiers, session data, telemetry, or internal debugging fields.

get-filelist

Updates user preferences stored in the backend user profile, limited to preferred UI language. The tool only returns the saved language preference and does not return account state, personal identifiers, session data, telemetry, or internal debugging fields.

set-user-preferences