(play.ht)

257 points amrrs | 4 comments | 14 Oct 24 19:16 UTC | HN request time: 1.124s | source

1. DevX101 ◴[14 Oct 24 20:27 UTC] No.41841586[source]▶

Has anyone done a comparison of combined speech to text and TTS vs speech-to-speech for create audio only interfaces? Particularly curious around latency, and quality of audio output.

replies(2): >>41841719 #>>41846399 #

2. amrrs ◴[14 Oct 24 20:39 UTC] No.41841719[source]▶

>>41841586 (TP) #

Hugging Face has got a TTS leaderboard (arena like lmsys) - https://huggingface.co/spaces/TTS-AGI/TTS-Arena

3. yavorgiv ◴[15 Oct 24 08:44 UTC] No.41846399[source]▶

>>41841586 (TP) #

Latency from the announcement https://x.com/_mfelfel/status/1846025183993511965/photo/1

replies(1): >>41850983 #

4. stuxyz ◴[15 Oct 24 17:37 UTC] No.41850983[source]▶

>>41846399 #

also here: https://x.com/play_ht/status/1846240712125452469

↑

Play 3.0 mini – A lightweight, reliable, cost-efficient Multilingual TTS model