News for hackers. Stuff that matters.

A comment on Launch HN: Play.ht (YC W23) – Generate and clone voices from 20 seconds of audio.

Re:Launch HN: Play.ht (YC W23) – Generate and clone voices f... by devmunchies on Monday March 27, 2023 @01:05PM (#35329226)
How is the latency for real-time TTS? I remember kicking the tires several months back but went with one of the big 3 cloud providers since they had lower latency.

I also like that the cloud provider supports SSML and I can explicitly configure the emotion, whereas Playht dynamically changed the emotion based on context of the text.

[ Parent | on HN ]
Re:Launch HN: Play.ht (YC W23) – Generate and clone voices f... by hammadh on Monday March 27, 2023 @01:38PM (#35329715)
The latency is not real-time yet but we're working on getting it to near real time. Regarding controlling the voice, we've added a few params like rate, voice guidance and temperature but for the most part the emotion is dependent on the text for now.
[ Parent | on HN ]
Re:Launch HN: Play.ht (YC W23) – Generate and clone voices f... by barbariangrunge on Tuesday March 28, 2023 @10:41AM (#35341903)
The dream for scammers
[ Parent | on HN ]
Re:Launch HN: Play.ht (YC W23) – Generate and clone voices f... by oceanplexian on Monday March 27, 2023 @01:12PM (#35329326)
Low latency would open up a whole lot of interesting applications. Even Elevenlabs doesn't seem to have low enough latency in my testing to work as a convincing voice assistant or to, for example, work in real time on a phone call. For that we likely need QUIC or some kind of streaming protocol.
[ Parent | on HN ]