How can I create a sequence with “exact text and pauses” like this:
“Hi, ich bin Erik, schön dich zu sehen! Wir sind hier im Raum für Robotik. Lass uns zusammen diesen Museumsbereich erkunden.”
pause one second.
„Die Exponate in diesem Raum sind unterschiedlichen Themen oder Gruppen zugeordnet."
When I add <speak>, I get the given text, but “pause one second” is also “spoken”. Any way to do this? Or something very similar with pauses?
Using <speak>, what exactly happens? Is everything between <speak> and </speak> send to 11Labs? Then I have to see how to use pauses in 11Labs?
Hi @info_AM, currently we don’t support any form of SSML tags or any such format for audio generation, which might let you control output audio attributes.
And yes while using the tag, everything in between the tags are sent for audio generation.
Hi @Deepankar_Acharyya,
thanks for the reply. Do you have any idea of how to create pauses within a text? Like “…” or any other letter / text etc.?
Or is it possible to give special instructions in a section? Our NPC is a museums guide. Sample dialog:
"This is your favorite item of the exhibition. Speak very enthusiastic about it.
This item is the ball from the soccer World Cup 2014. Germany won in Brazil. …"
Meaning that with the first two sentences I can give the NPC a special mood. Does this work somehow? Any recommendations what works beste?