[HN Gopher] Play Dialog: A contextual turn-taking TTS model like...
___________________________________________________________________
Play Dialog: A contextual turn-taking TTS model like NotebookLM
Playground
Author : dulldata
Score : 34 points
Date : 2024-11-13 19:36 UTC (3 hours ago)
(HTM) web link (play.ai)
(TXT) w3m dump (play.ai)
| dulldata wrote:
| if you are developer, then there's an api -
| https://docs.play.ai/tts-api-reference/endpoints/v1/tts/stre...
| treesciencebot wrote:
| i don't think anyone has done real-time multi-speaker dialog
| generation before
| Asjad wrote:
| Impressed by the voice quality PlayDialog achieves in real-time
| streaming, it sounds incredibly natural
| mahmoudfelfel wrote:
| PlayAI (fma PlayHT) founder here, this is a native multiturn
| voice model that is built for conversations like real-time agents
| or podcasts. Try it through our playground
| (https://play.ai/playground) or API (https://docs.play.ai/). Feel
| free to ask anything.
| guytv wrote:
| Ouch. If you know Arabic or Hebrew, try selecting those languages
| and typing something in--it's hilarious.
|
| Looks like they're "testing in production."
| mahmoudfelfel wrote:
| The current deployed model is English only, we are rolling out
| a multilingual version later this week!
___________________________________________________________________
(page generated 2024-11-13 23:00 UTC)