Turn a voice note into a table
voice_to_sheetUse this when the user has a voice note that lists things (expenses, orders, stock counts, hours worked) and wants it as a table. Pass the attached audio as file, or audio_url, or audio_base64 (ogg, opus, m4a, mp3, wav, webm, flac or amr; up to about 3 minutes); add language when known. It transcribes the note with free speech-to-text, then copies it into rows and columns. Returns the table, the transcript, the values that may be misheard (unclear), sum checks, CSV text and 24-hour links. Not for meeting transcripts or subtitles.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| file | No | The voice note the user attached in the chat. | |
| hint | No | Optional: what the content is or which columns the person wants, for example 'stock count, item and quantity only'. | |
| language | No | Optional ISO 639-1 code of the spoken language, such as en, vi, es or sw. Without it the language is detected. | |
| audio_url | No | A public https link to one voice note (ogg, opus, m4a, mp3, wav, webm, flac or amr), up to 6 MB, about 3 minutes. | |
| audio_base64 | No | The audio bytes as base64, up to 6 MB. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| csv | Yes | ||
| kind | Yes | ||
| rows | Yes | ||
| links | Yes | ||
| notes | Yes | ||
| title | Yes | ||
| checks | Yes | ||
| notice | Yes | ||
| source | Yes | ||
| status | Yes | ||
| totals | Yes | ||
| columns | Yes | ||
| message | Yes | ||
| unclear | Yes | ||
| currency | Yes | ||
| transcript | Yes |