@vocalstack/mcp 1.2.0 → 1.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -61,24 +61,21 @@ Both offer the same tools.
61
61
  ## Tools
62
62
 
63
63
  <!-- tools -->
64
- - `transcribe_url`: Start transcribing a recorded audio or video at a public link: a media file, a podcast episode, a YouTube video, or a public post on one of the sites listed under url.
65
- - `transcribe_file`: Start transcribing an audio or video file you hold, sent whole as base64 (at most 10 MiB decoded; mp3, m4a, wav, mp4, webm and other common formats).
66
- - `get_transcription`: Read one transcription's text, with timestamps and speakers, and its status.
67
- - `wait_for_transcription`: Wait until a file or link transcription finishes, up to timeoutS seconds (default 50, at most 60), and return its status without the text.
68
- - `list_transcriptions`: List this account's transcriptions (files, links and live ones, including those recorded by broadcasts), newest first, one page at a time.
69
- - `search_transcriptions`: Find the lines where given words or a name were said, across all of this account's transcriptions or in one (transcriptionId).
70
- - `search_by_meaning`: Find the passages closest in meaning to a question or topic, across this account's transcriptions or in one (transcriptionId), in any language and even when they share none of its words.
71
- - `get_summary`: Get the title and summary of a finished transcription.
72
- - `translate_transcription`: Get a whole finished transcription translated into another language, in the same text or segments shape as get_transcription.
73
- - `rename_speaker`: Name a speaker in one transcription, so its transcript shows the name instead of "Speaker N".
74
- - `delete_transcription`: Delete a transcription: it moves to the trash with its recordings, transcript, translations and summary, and its share links stop working.
75
- - `list_voices`: List the voices that can read translations aloud in one language: stock voices and this account's own cloned voices.
76
- - `set_cloned_voices`: Turn cloned voices on or off for one transcription's spoken translations.
77
- - `list_speakers`: List the speakers this account has saved: people named once so they are recognised by name in later transcriptions.
78
- - `list_broadcasts`: List this account's broadcasts, most recently updated first (up to 500, no paging).
79
- - `get_broadcast`: Get one broadcast in detail: whether it is on air, its public link, the transcriptions it recorded and the stream addresses it uses.
80
- - `start_broadcast`: Start live transcription and translation of a live stream (YouTube live, internet radio, HLS .m3u8 or Icecast).
81
- - `stop_broadcast`: Stop the live transcription a broadcast is running (started with start_broadcast), which also stops its billing.
64
+ - `create_transcription`: Start transcribing a finished recording, from a public link or a file sent inline; returns a transcriptionId at once, before any text.
65
+ - `get_transcription`: Read one transcription's status and text, with timestamps and speakers: as it was spoken or translated, at once or after waiting for it to finish.
66
+ - `list_transcriptions`: List this account's transcriptions, newest first, a page at a time: files, links and live ones, including those broadcasts recorded.
67
+ - `search_transcriptions`: Find what was said across this account's transcriptions, or in one: the lines with given words or a name (mode words), or the passages that answer a question (mode meaning).
68
+ - `get_summary`: Get the title and summary of a finished transcription, writing one the first time if it has none.
69
+ - `rename_speaker`: Name or rename a speaker: one person in one transcription, so its transcript shows the name instead of "Speaker N", or a saved speaker, everywhere they are recognised.
70
+ - `delete_transcription`: Move a transcription to the trash, with its recordings, transcript, translations and summary; its share links stop working.
71
+ - `set_cloned_voices`: Turn cloned voices on or off for spoken translations: for one transcription, or for one saved speaker everywhere they are recognised.
72
+ - `list_speakers`: List the speakers this account has saved: people recognised by name in every new transcription.
73
+ - `save_speaker`: Save one speaker of a transcription to the account's saved speakers, so later transcriptions recognise and name them; their own speech in this transcription is the sample.
74
+ - `delete_speaker`: Delete a saved speaker for good: their name, fingerprint, stored sample and any cloned voice are erased at once and cannot be restored.
75
+ - `list_broadcasts`: List this account's broadcasts, or get one in detail.
76
+ - `start_broadcast`: Start live transcription and translation of a stream playing now, on a public link listeners open in their own language.
77
+ - `stop_broadcast`: Stop the live transcription a broadcast is running, which also stops its billing.
78
+ - `delete_broadcast`: Move a broadcast to the trash: its public link and stream addresses stop working for listeners.
82
79
  <!-- /tools -->
83
80
 
84
81
  Errors come back as tool results with `isError` set and a body with `error` (a code such as `not_found`, `invalid_options`, `invalid_state`, `insufficient_credit` or `rate_limited`), `message`, `retryable`, `retryAfterS` and `topUpUrl` when credit is needed. Retry a start with the same `idempotencyKey` so nothing is made or billed twice.