Previous value: -"true, and only after the user has said they own this recording or have the rights to transcribe it. false is refused with rights_not_confirmed; ask the user first."New value: +"true, and only after the user has said they own this recording or have the rights to transcribe it. false is refused with rights_not_confirmed (ask the user first), except for a link to a public video on a social platform, which needs no statement."

Previous value: -"Direct link to an audio or video file the user owns or may use, such as https://example.com/talk.mp3. Give this or file, not both. Pages of YouTube, TikTok or other platforms are refused."New value: +"Link to a public video on TikTok, Instagram, Facebook, X, Vimeo or another social platform (its audio is read and transcribed), or a direct link to an audio or video file, such as https://example.com/talk.mp3. Give this or file, not both. For a YouTube link call get_transcript instead."

Added value: +{
+  "description": "Seconds of audio transcribed when partial is true.",
+  "minimum": 0,
+  "type": "integer"
+}

Added value: +{
+  "description": "True when only the first covered_seconds of a longer recording were transcribed within the 30-second interactive call budget.",
+  "type": "boolean"
+}

Removed value: -{
-  "description": "Seconds of audio transcribed when partial is true.",
-  "minimum": 0,
-  "type": "integer"
-}

Removed value: -{
-  "description": "True when only the first covered_seconds of a longer recording were transcribed within the 30-second interactive call budget.",
-  "type": "boolean"
-}

Added value: +{
+  "description": "Seconds of audio transcribed when partial is true.",
+  "minimum": 0,
+  "type": "integer"
+}

Added value: +{
+  "description": "True when only the first covered_seconds of a longer recording were transcribed within the 30-second interactive call budget.",
+  "type": "boolean"
+}

Previous value: -"Set true only after the user has said they own this recording or have the rights to transcribe it."New value: +"true, and only after the user has said they own this recording or have the rights to transcribe it. false is refused with rights_not_confirmed; ask the user first."

Previous value: -"An audio or video file the user uploaded to the chat."New value: +"An audio or video file the user uploaded to the chat (ChatGPT fills this in). Give this or url, not both."

Added value: +"Name of the file, such as episode-4.mp3. Used as the title when title is left out."

Added value: +"Media type of the file, such as audio/mpeg or video/mp4."

Previous value: -"The library_id that transcribe_media returned. Only needed when transcribe_media returned one; leave it out otherwise."New value: +"Leave out on the first transcription. Pass the library_id from an earlier transcribe_media answer, such as lib_9b6a98861ea4f54bff8f5cf1, to add this transcript to that same library, so search_transcripts finds both together."

Previous value: -"Direct https link to an audio or video file the user owns or may use, such as https://example.com/talk.mp3. Pages of video or social platforms are not accepted. Give this or file."New value: +"Direct link to an audio or video file the user owns or may use, such as https://example.com/talk.mp3. Give this or file, not both. Pages of YouTube, TikTok or other platforms are refused."

Added value: +"uri"

Added value: +"^https?://"

Added value: +"The UTC day of the answer, such as 2026-10-10."

Added value: +"date"

Added value: +"Length of the recording, in whole seconds."

Added value: +0

Added value: +"When the transcript is deleted, as an ISO 8601 UTC time."

Added value: +"date-time"

Added value: +"Spoken language as an ISO 639-1 code, such as en."

Previous value: -"Present when the caller has no user id; pass it to the other tools to reach this transcript."New value: +"A string when the caller has no ChatGPT user id: pass it as library_id to the other tools and to later transcribe_media calls. null otherwise."

Added value: +"The speech model, such as @cf/openai/whisper-large-v3-turbo."

Added value: +"Timestamped stretches of speech (when include has segments)."

Added value: +"End, in seconds from the beginning of the recording."

Added value: +0

Added value: +"Start, in seconds from the beginning of the recording."

Added value: +0

Added value: +"The words spoken in this stretch."

Added value: +"Host the file was read from; null for an upload."

Added value: +"upload for a file from the chat, url for a link."

Added value: +"SRT captions with numbered cues (when include has srt)."

Added value: +"ok: the file was transcribed. A refused call returns no object, only an error text such as \"transcript_not_found: ...\" that says what to do next."

Added value: +"The title given, or the file name."

Added value: +"Id of a saved transcript, for suggest_clips and translate_subtitles."

Added value: +"^tr_[0-9a-f]{16}$"

Added value: +"Audio seconds this call used from today's allowance."

Added value: +0

Added value: +"Audio seconds the caller can still transcribe today (UTC)."

Added value: +0

Added value: +"WebVTT captions (when include has vtt)."

Added value: +"Words in the transcript."

Added value: +0

Removed value: -{
-  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
-  "type": "string"
-}

Added value: +{
+  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
+  "type": "string"
+}