Not sure if this exists but i'm approaching a need for it.
Creating a vtt transcript from a video & text.
Audiobooks and songs have the text already, it just needs to be timestamped to when it appears in the media file. Logically this should take less CPU and improve accuracy over current blind transcripting services.
err head /
npub19s…8v4g8
2024-04-13 15:59:22
Author Public Key
npub19sejf348xa9maq43kj3fnzgh0lk4v7qufk4q6wz7t3jgjhc937qqu8v4g8Published at
2024-04-13 15:59:22Event JSON
{
"id": "987c5c684ee025e66f9899339dcc27de860789ea1f5fa3485f6a072891ae28bc",
"pubkey": "2c3324c6a7374bbe82b1b4a29989177fed56781c4daa0d385e5c64895f058f80",
"created_at": 1713023962,
"kind": 1,
"tags": [
[
"proxy",
"https://podcastindex.social/users/errhead/statuses/112264738380924191",
"activitypub"
]
],
"content": "Not sure if this exists but i'm approaching a need for it.\n\nCreating a vtt transcript from a video \u0026 text.\n\nAudiobooks and songs have the text already, it just needs to be timestamped to when it appears in the media file. Logically this should take less CPU and improve accuracy over current blind transcripting services.",
"sig": "6c349c8cbdb10246ce55898e02ebb27f44b6aebfabe0fbfc6116b60e472c8b9696baef30751b96a91644350cdf6047126d5994cc97307348c4eae42561c8dd97"
}