Introducing Google Cloud Natural Language API, Speech API and New Data Center
cloudplatform.googleblog.com
Introducing Google Cloud Natural Language API, Speech API and New Data Center
1–10 of 51 posts
Re: Introducing Google Cloud Natural Language API, Speech API and New Data Center
#2Free till August 1st (with request limit) and then there'll be a free tier.
Pricing is here: https://cloud.google.com/natural-language/pricing
Re: Introducing Google Cloud Natural Language API, Speech API and New Data Center
#3Regarding non-streaming transcription: It doesn't seem like the return includes timings, which would limit its usefulness in transcription for accessibility (where, for example, a post-processing step on our side would consume the Cloud Speech API and build SRT subtitle files for class recordings)
Is there a product / service / library out there that could help align a known-good transcript with the original audio (creating the timings) if the Cloud Speech API doesn't plan to return timings?
Re: Introducing Google Cloud Natural Language API, Speech API and New Data Center
#4Regarding non-streaming transcription: It doesn't seem like the return includes timings, which would limit its usefulness in transcription for accessibility (where, for example, a post-processing step on our side would consume the Cloud Speech API and build SRT subtitle files for class recordings) Is there a product / service / library out there that could help align a known-good transcript with the original audio (c…
Why would you need the Speech API if you already have a known-good transcript?
Re: Introducing Google Cloud Natural Language API, Speech API and New Data Center
#5Regarding non-streaming transcription: It doesn't seem like the return includes timings, which would limit its usefulness in transcription for accessibility (where, for example, a post-processing step on our side would consume the Cloud Speech API and build SRT subtitle files for class recordings) Is there a product / service / library out there that could help align a known-good transcript with the original audio (c…
Why would you need the Speech API if you already have a known-good transcript?
I'm sorry if I was unclear. If I used the Cloud Speech API to produce the transcript, is there another library/service/etc that would align it to the original audio again.
Re: Introducing Google Cloud Natural Language API, Speech API and New Data Center
#6Regarding non-streaming transcription: It doesn't seem like the return includes timings, which would limit its usefulness in transcription for accessibility (where, for example, a post-processing step on our side would consume the Cloud Speech API and build SRT subtitle files for class recordings) Is there a product / service / library out there that could help align a known-good transcript with the original audio (c…
Yeah that was a bummer to see in the alpha and I was holding out that they'd expose that data at release date (as IBM Watson has), but maybe they want to limit the ability for competitors to easily appropriate the sound-to-transcribed-word data.
Re: Introducing Google Cloud Natural Language API, Speech API and New Data Center
#7On the other side of the NLP spectrum, what players out there are involved in NLG (natural language generation)? I've seen Arria and a couple other small projects, but I'm just starting to investigate the space and haven't found a whole lot yet.
Re: Introducing Google Cloud Natural Language API, Speech API and New Data Center
#8Regarding non-streaming transcription: It doesn't seem like the return includes timings, which would limit its usefulness in transcription for accessibility (where, for example, a post-processing step on our side would consume the Cloud Speech API and build SRT subtitle files for class recordings) Is there a product / service / library out there that could help align a known-good transcript with the original audio (c…
Yeah that was a bummer to see in the alpha and I was holding out that they'd expose that data at release date (as IBM Watson has), but maybe they want to limit the ability for competitors to easily appropriate the sound-to-transcribed-word data.
Thanks for mentioning Watson; I keep meaning to go back to it and see how limits have improved.
Re: Introducing Google Cloud Natural Language API, Speech API and New Data Center
#9So how long until these new services get summarily discontinued?
Re: Introducing Google Cloud Natural Language API, Speech API and New Data Center
#10Earlier quoted context omitted.
Why would you need the Speech API if you already have a known-good transcript?
I'm sorry if I was unclear. If I used the Cloud Speech API to produce the transcript, is there another library/service/etc that would align it to the original audio again.
Watson does this, VoiceBase does this and I believe HP and MS do this... it's very common for speech API's to provide time offset information for each word.