> (them) That's very low quality though, and our feedback from blind users indicated that old TTS methods like that aren't usable (such as RHVoice).
> See > [> https://>; social.highenergymagic.net/@Gr> [email protected]/116638788131682457](GrapheneOS (npub1kwa…e0nj)/116638788131682457">https://social.highenergymagic.net/GrapheneOS (npub1kwa…e0nj)/116638788131682457 )
> It will be improved, but there's a starting point for everything. We didn't want to delay it too much, but the current target was similar latency to Google's Speech Recognition & Synthesis, but perhaps it isn't as fast at higher speeds?
> Let's focus on actionable goals! Where could the latency be improved? Is it perhaps too slow at very high speeds?
> (me) maybe a setting could be offered so that users can choose which they want?
> (them) Maybe! Configuring the amount of "effort" to make it faster was something we wanted but it wasn't working out initially and we didn't want to delay the release for that.
> But what are the exact latency issues? We need clear targets.
> for example, currently the TTFA (time-to-first-audio) is ~150 ms on a Pixel 8a.
solo
npub1hl…6qven
2026-05-26 07:21:31 CEST
in reply to nevent1q…3s4u
Author Public Key
npub1hllq64qeth88xc97gt9l734sflguy6mxrt7hq8w2jtc6r8lvm8qsn6qvenSeen on
wss://relay.momostr.pinkPublished at
2026-05-26 07:21:31 CESTEvent JSON
{
"id": "5c4e0369f92fd97c494849cbe38fb0bfc21b181dbc401286f492732bd6c99672",
"pubkey": "bffe0d54195dce7360be42cbff46b04fd1c26b661afd701dca92f1a19fecd9c1",
"created_at": 1779772891,
"kind": 1,
"tags": [
[
"e",
"ce6b5b0da39c3752050f1c15bf1af20a59cadc0a63c43f20adf73e64e21e9c97",
"",
"reply",
"bffe0d54195dce7360be42cbff46b04fd1c26b661afd701dca92f1a19fecd9c1"
],
[
"p",
"bd2bb82d84762b6b290c509a800d7092c03eefa6fdaa52f6a962d90acf39852e"
],
[
"e",
"e7ce700cf4c0325846ac1fef6057ab817f9c380c6e5208d2d2bd92046a409ce3",
"",
"root",
"bd2bb82d84762b6b290c509a800d7092c03eefa6fdaa52f6a962d90acf39852e"
],
[
"p",
"bffe0d54195dce7360be42cbff46b04fd1c26b661afd701dca92f1a19fecd9c1"
],
[
"p",
"b3ba3c5045fbaf99be9cb4daa9f1d7baeedaba0fc5b91596511e2fb7a70dd7f9"
],
[
"proxy",
"https://tech.lgbt/@solonovamax/116639196232806227",
"web"
],
[
"proxy",
"https://tech.lgbt/users/solonovamax/statuses/116639196232806227",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://tech.lgbt/users/solonovamax/statuses/116639196232806227",
"pink.momostr"
],
[
"-"
]
],
"content": "\u003e (them) That's very low quality though, and our feedback from blind users indicated that old TTS methods like that aren't usable (such as RHVoice).\n\n\u003e See \u003e [\u003e https://\u003e social.highenergymagic.net/@Gr\u003e [email protected]/116638788131682457](https://social.highenergymagic.net/nostr:npub1kwarc5z9lwhen05uknd2nuwhhthd4ws0cku3t9j3rchm0fcd6luslse0nj/116638788131682457 )\n\n\u003e It will be improved, but there's a starting point for everything. We didn't want to delay it too much, but the current target was similar latency to Google's Speech Recognition \u0026 Synthesis, but perhaps it isn't as fast at higher speeds?\n\n\u003e Let's focus on actionable goals! Where could the latency be improved? Is it perhaps too slow at very high speeds?\n\n\u003e (me) maybe a setting could be offered so that users can choose which they want?\n\n\u003e (them) Maybe! Configuring the amount of \"effort\" to make it faster was something we wanted but it wasn't working out initially and we didn't want to delay the release for that.\n\n\u003e But what are the exact latency issues? We need clear targets.\n\n\u003e for example, currently the TTFA (time-to-first-audio) is ~150 ms on a Pixel 8a.",
"sig": "54128955d63c29aa9011e6c9d5a560e28c550f5fc3ed9774151d8b5c2aef87124889dd1c7e498b5024cb5ecf666adc88083c45374591233b6fc70a2f92e07885"
}