juraj on Nostr: whisper for speech to text, then a model like openvoice2 that can render text to ...
whisper for speech to text, then a model like openvoice2 that can render text to speech in infinite accents and styles. distortion is not enough.
as for the identities, SimpleX has a nice model. no permanent identities, just rendezvous strings.
could be a fun hacking project. the latency is going to be horrible though.
Published at
2024-05-03 00:41:57Event JSON
{
"id": "3331aca1ce0219544ee53c2726583bc1a78e4a66114f4615a1eb87667cdf5fbd",
"pubkey": "dab6c6065c439b9bafb0b0f1ff5a0c68273bce5c1959a4158ad6a70851f507b6",
"created_at": 1714689717,
"kind": 1,
"tags": [
[
"p",
"b7ed68b062de6b4a12e51fd5285c1e1e0ed0e5128cda93ab11b4150b55ed32fc"
],
[
"e",
"53d9741e399eeacc4388a8d8c5753703b905b002d75b818fd9466beabdf5bcfa",
"wss://nostr.hekster.org",
"root"
]
],
"content": "whisper for speech to text, then a model like openvoice2 that can render text to speech in infinite accents and styles. distortion is not enough. \n\nas for the identities, SimpleX has a nice model. no permanent identities, just rendezvous strings. \n\ncould be a fun hacking project. the latency is going to be horrible though.",
"sig": "e1e533f11b0c3d6b2b137125f8622dce2bb75e0192ac7870e6e17378e57070110f9c49119762065a8ba2f8f967328494a2cec26823b0ed167980b2a4e3f693be"
}