Here's what the raw data of the unit selection db file for SpeakEasy sounds like.
-
@rommix0 is that 8-bit linear PCM?
@BorrisInABox nah, it's 16 bit. I'm sure the data has subheaders.
-
R relay@relay.mycrowd.ca shared this topic
-
@BorrisInABox nah, it's 16 bit. I'm sure the data has subheaders.
@rommix0 Wow, really? Sounds very 8-bit or less in that clip.
-
@rommix0 Wow, really? Sounds very 8-bit or less in that clip.
@BorrisInABox you would think that
-
@BorrisInABox you would think that
@rommix0 @BorrisInABox Or some kind of compressed.
-
@rommix0 @BorrisInABox Or some kind of compressed.
@x0 @BorrisInABox yeah like adpcm
-
@datajake1999 in a way, yeah. It's like MBROLA, but not actually MBROLA since speakeasy is proprietary.
@rommix0 @datajake1999 Yeah I definitely recognise that as diphone based synthesis.
-
Here's what the raw data of the unit selection db file for SpeakEasy sounds like. It gives you a good idea on how unit selection synthesis works.
@rommix0 i think it's diphone, specifically, the embrola en1 database
-
@rommix0 i think it's diphone, specifically, the embrola en1 database
@spacepup Nah. en1 is english but with a foreign speaker. The speaker used for SpeakEasy is not a foreigner.
-
Here's what the raw data of the unit selection db file for SpeakEasy sounds like. It gives you a good idea on how unit selection synthesis works.
@rommix0 sounds like a fucked up vocal warmup
-
Here's what the raw data of the unit selection db file for SpeakEasy sounds like. It gives you a good idea on how unit selection synthesis works.
@rommix0 what is speak easy?
-
@rommix0 what is speak easy?
@keao tts synth
