The chip is an 8-bit DSP which uses LPC-compressed diphone samples. The diphones can either be stored on the chip's internal ROM or loaded from memory. The phonemes, and accompanying prosodic information, are streamed to the chip, which it uses to generate the speech by concantenation of the compressed diphones.
The TI99/4A was ahead of it's time, but the speech synthesizer was way WAY ahead of it's time and was easily affordable to the many in the early 1980's. I had one when most people were still using ZX81's or the 1st 16K Spectrum which was a long behind in technology. It's terrible it wasn't more popular than it was as it was amazing to hear speech like that then.
It amazes me how the old TI computer uses words more naturally than most modern speech synthesizers. Why can't Microsofts Sam sound as natural as this when? It's all a big ? to me.
Woah. I never realized the TI-99 had such a clear voice synthesizer. I think it can still complete with most of today's voice synthesizers. It's clear and you can understand it.
Hi. Yes I am continually amazed at it. And also at the level of compression. The data that does the talking is 98% smaller than the WAV file that I used as a source! Glad you liked it!
@yeowza9 Something sounds kind of fishy with that demo. That doesn't sound like a "speech" program, (like Windows Narrator) as much as it does just....."sampled" voice, some how played back, via the TI99, utilizing a low sample rate. It sounds "weird", cool, amazing, but weird. Like a "real" person.
Aw, heck, son! That was cool! Email me. Will there be a speech tutorial for Win99/4A users? How do I do what you did, and go beyond the limits of the resident list of words in the speech synthesizer. So far I haven't been able to understand CALL SPGET. Also can't use Terminal emulator and XB at the same time.
scary...
duftmand 5 months ago
Nice work dude, wish I could take a better look at the code.
metabog 5 months ago
Wow! It almost sounds kinda real! :D
MrChiknman 8 months ago
The chip is an 8-bit DSP which uses LPC-compressed diphone samples. The diphones can either be stored on the chip's internal ROM or loaded from memory. The phonemes, and accompanying prosodic information, are streamed to the chip, which it uses to generate the speech by concantenation of the compressed diphones.
douro20 9 months ago
hmm, that was a synthesized speech? i have problems to believe that..its sounds so human.
Serpico261 1 year ago
@Serpico261 That's what I said........
gjc82071 9 months ago
I don't understand... why did you start with WAV file if this is true speech synthesis????
neons99 1 year ago
Wow. That was amazing. That was better than my Mac 15 or even 20 years later.
marktrade88 2 years ago
the phonics are every bit as good if not better than my currah64, and several years younger ?
sonick808 2 years ago
The TI99/4A was ahead of it's time, but the speech synthesizer was way WAY ahead of it's time and was easily affordable to the many in the early 1980's. I had one when most people were still using ZX81's or the 1st 16K Spectrum which was a long behind in technology. It's terrible it wasn't more popular than it was as it was amazing to hear speech like that then.
pjcnet 2 years ago
thank for for this.
angelomcm 3 years ago
It amazes me how the old TI computer uses words more naturally than most modern speech synthesizers. Why can't Microsofts Sam sound as natural as this when? It's all a big ? to me.
Filosofen88 3 years ago
Woah. I never realized the TI-99 had such a clear voice synthesizer. I think it can still complete with most of today's voice synthesizers. It's clear and you can understand it.
yeowza9 3 years ago
Hi. Yes I am continually amazed at it. And also at the level of compression. The data that does the talking is 98% smaller than the WAV file that I used as a source! Glad you liked it!
MarkWillsUK 3 years ago
@yeowza9 Something sounds kind of fishy with that demo. That doesn't sound like a "speech" program, (like Windows Narrator) as much as it does just....."sampled" voice, some how played back, via the TI99, utilizing a low sample rate. It sounds "weird", cool, amazing, but weird. Like a "real" person.
gjc82071 1 year ago
@gjc82071
This is synthesized speech created using phonemes and prosodic information generated from an actual recording.
douro20 9 months ago
Aw, heck, son! That was cool! Email me. Will there be a speech tutorial for Win99/4A users? How do I do what you did, and go beyond the limits of the resident list of words in the speech synthesizer. So far I haven't been able to understand CALL SPGET. Also can't use Terminal emulator and XB at the same time.
orion1052003 3 years ago
He he! Speech tutorial? Your wish is my command! Just click on the video response above and enjoy!
Regards,
Mark.
MarkWillsUK 3 years ago
@orion1052003
The speech is synthesized using phonemes and prosodic information contained in the code. It is not being generated using a dictionary.
douro20 9 months ago