Google voice API https://texttospeech.googleapis.com/v1/voices doesn't have French voice.
fr-FR-Standard-A
fr-FR-Standard-C
fr-FR-Wavenet-A
fr-FR-Wavenet-C
fr-FR-Wavenet-D
fr-FR-Wavenet-E
There are various French(France), French(Canadian) Male and Female voices while using Text-to-Speech in GCP.
You can see this document that shows all the supported voices while using Text-to-Speech.
Additionally you can create a Custom voice while training a model, but for this you need to contact a member of the sales team.
Related
If I send kittens to Google Cloud Text-to-Speech can it return ˈkɪtnz? I need a Text-to-Speech service that provides both audiofiles and IPA transcriptions. The Oxford English Dictionary and IBM Watson will return both. Can Google Cloud do this?
Yes, Google Cloud Text-to-Speech can convert a text with IPA transcriptions by using Speech Synthesis Markup Language (SSML) phoneme tag. This tag can help you produce custom pronunciations, and on your end, IPA transcriptions.
This block of code can produce the pronunciation of kittens in IPA phoneme in English (United Kingdom), en-GB.
<speak>
<phoneme alphabet="ipa" ph=ˈkɪtnz>kittens</phoneme>
</speak>
Take note that there are different phonemes and levels of stress for each language. The ˈkɪtnz is under English (United Kingdom). You can go through this documentation to see the supported phonemes and levels of stress.
does have any company that provides Apis for this service?
Speech, audio Analytics,
Automated speech recognition,
multiple speaker separation,
emotions,
speakers overlapping (detect speakers that speak at the same time).
my project needs to detect the speakers on audio and separate them and also detect if they have any collision (overlapping) between speakers ( speak together).
now I use DeepAffect, but they have bad support so I searching for another company that deals with that issue
Note: services that I wrote below I already checked and it's not useful for my goals.
-symbl.ai
-Cloud Speech-to-Text - Speech Recognition | Google Cloud
-azure cognitive-services
-AI-Powered Speech Analytics for Amazon Connect
Its not so clear which type of setup you expect/have.
Cloud service? On-Prem? What sizing?
You can check the following company Phonexia that provide such solution. https://www.phonexia.com/en/
Here list of APIs and capabilities their solution may provide: https://download.phonexia.com/docs/spe/
So I created this trivia game on Actions on Google for the Google Assistant, and one of the options is to choose the voice/personality that will talk when you're playing the game. I chose the "Mr. Montgomery" voice. You can hear the voice for yourself here https://developers.google.com/actions/templates/trivia
I published the game, but when I try it on my Google Home, it's not using the Mr Montgomery voice, it's using the voice set in this other option I found that lets you choose the voice gender but it doesn't give an example. I changed it to male and it is a male voice, but it isn't the Mr Montgomery voice given in the preview. Is there something else I have to do to make it use the Mr Montgomery voice?
For google home actions, can I use my own voice or someone else's voice with permission? Can I read the text responses, record them, and play them back as audio files?
Earplay is an example on Alexa:
https://www.amazon.com/gp/product/B01K8V6NSI?ie=UTF8&path=%2Fgp%2Fproduct%2FB01K8V6NSI&ref_=skillrw_dsk_si_dp&useRedirectOnSuccess=1&
A guy from Gupshup said that it is not allowed:
https://youtu.be/f-mPuEbJ-nU?t=45m13s
I didn't see where it was not allowed in the terms of service.
"the platform does not allow that" does not mean that it is legally not allowed, but that it is simply not possible.
Both Alexa and Google Assistant have a default voice which can not be changed.
When developing an Action, you can select from one of four voices (two male, two female) to use. You can't use the default Google Assistant voice. There is no technical way to use another voice.
While you can send audio files, and these audio files can contain a voice, this would be a lot of work for little benefit.
Yes, Progressive does this with their Google Action.
I am using mary tts 5.1 and the voice dfki-prudence (English female).
This voice variation is not working (in emotions like happy, sad, angry, etc.). But this emotion is working in the voice cmu-slt-hsmm(English female). Voice dfki-prudence(English female) is good.
How do I make changes in the dfki-prudence (English female) voice variation? Anyone know?
The dfki-prudence voice does not support the expressive styles.
Only dfki-pavoque-styles has this feature.
It is the answer from official github.