New project: a podcast version of my blogs. Locally generated. First the llm processes the blog into a form that is better for speech, another llm verifies that the first one did not screw it up. That should get the text blog into a more readable form. Then I do speech to text, which I verify via text to speech, I also change the parameters automatically if the output is not good.
I even had to change the phonemizer, to recode the inference model a bit.
Text to speech components are on my github.
The podcast is value4value enabled, so I accept sats per minute if your podcasting app supports it and boosts. The boosts are directly integrated with my podcasting 2.0 dashboard (also on my github).
https://fountain.fm/show/3MjdPUN26O8yQAtaXBmL
Juraj
npub1m2…lr8p9
2024-11-12 09:06:05
Author Public Key
npub1m2mvvpjugwdehtaskrcl7ksvdqnnhnjur9v6g9v266nss504q7mqvlr8p9Published at
2024-11-12 09:06:05Event JSON
{
"id": "4656f0aaaa6d60e1bda057c6142d00af8034485c407bb270d2f7fcd961f09eef",
"pubkey": "dab6c6065c439b9bafb0b0f1ff5a0c68273bce5c1959a4158ad6a70851f507b6",
"created_at": 1731402365,
"kind": 1,
"tags": [],
"content": "New project: a podcast version of my blogs. Locally generated. First the llm processes the blog into a form that is better for speech, another llm verifies that the first one did not screw it up. That should get the text blog into a more readable form. Then I do speech to text, which I verify via text to speech, I also change the parameters automatically if the output is not good.\n\nI even had to change the phonemizer, to recode the inference model a bit. \n\nText to speech components are on my github.\n\nThe podcast is value4value enabled, so I accept sats per minute if your podcasting app supports it and boosts. The boosts are directly integrated with my podcasting 2.0 dashboard (also on my github).\n\nhttps://fountain.fm/show/3MjdPUN26O8yQAtaXBmL\n",
"sig": "edebf3fe0ec0fa7c0403685b2f166eb062ea859d420be15060c5ed9589a50a62f5f4f3da3655658ef3c9fffe53679693eb2bc4819c0c93658e90cc253665bb95"
}