We made a major update to our mastering engine, updating libraries and improving performance 🚀 You should have less error rates and a better customer experience.
We're continuously working on our Voice Intelligence Layer.
A commonly asked question by customers is "how do I make sure the same SSML works across providers".
So today we're VERY excited to launch our first (of many) features 🎉 🎂
You can run this on ANY provider and it'll either work or it'll fail. So your code will work with ANY provider and ANY voice
body = {
"projectName": "__TEST",
"scriptText": '<as:section> hello <as:break time="4s"/> worlds </as:section>',
}
We showed this in beta to our customers and we got this quote
"This will save us so much time 10% of our bugs are due to things like this" - Software Developer at an Advertising company
How do I get started?
Simply to get stared just update
<break time="150ms"/>
to <as:break time="150ms"/>
If you want an update on SSML wikipedia is great.
Ballsy Rock
Chopper Horns
Chopper Strings
Clap Together
Cool Industries
Dark And Unsettling
Design Grove
Epic Brass Trap
Epic Pace
Ethereal Dream
Fascinating Technology
Friendly Electro Pop
Friendly Fantasy
Garage Banger
Indie Disco
Laid Back Funk
Piano Artist
Power Sports
Pulsing Out Score
Rainbow Rock
Relaxed Vacation
RelaXmas
Rockabilly Mischief
Stepping Up
Sunny Skies
Surfing Dog
Trailer Beast
Vintage Swing
Welcoming Piano
Wild Beast
Have fun sampling these :)
We've fleshed out our examples.
Video Voice Over use case for a video voice over use case
And we added to our github a news summarizer
We fixed some UX problems (thanks to our customers for pointing this out) in the Media endpoints.
You can now do a lot more with media files, namely, place the name of the media file directly in the script using the name="" attribute.
You can also use the id="" attribute to create a placeholder, that can be overwritten in the mastering call:
import audiostack
import os
audiostack.api_key = os.environ["AUDIO_STACK_DEV_KEY"]
response = audiostack.Content.Media.create(filePath="default.wav")
print(response)
mediaId = response.mediaId
script = """
<as:section name="intro" soundsegment="intro">
hello world <as:media name="default.wav" id="file1"/>
</as:section>
"""
script = audiostack.Content.Script.create(scriptText=script)
print(script)
speech = audiostack.Speech.TTS.create(scriptItem=script, voice="sara")
print(speech)
mastering = audiostack.Production.Mix.create(
speechItem=speech,
# mediaFiles={
# "file1" : <any media id of an uploaded file">
# }
)
print(mastering)
Our intern William built something cool 🆒
https://github.com/aflorithmic/news_article_summarizer have a look here at this news article summarizer - leveraging Beautiful Soup 😍, OpenAI 💯 and our AudioStack API, it takes a URL and produces a beautiful audio summary. Have a play!
We updated our library
You can see all of the multilingual voices - plus what languages they support.
As we build out the AudioStack we're constantly looking for improvements.
Exciting news! We've been hard at work collaborating with our providers to bring you more hyper-realistic English voices 🥳 We're thrilled to introduce 35 new voices from ElevenLabs, including 14 American accents 🇺🇸, 19 British accents 🇬🇧, and 2 Australian accents 🇦🇺. Additionally, we've added 41 voices from WellSaid Labs, featuring 28 American English 🇺🇸, 6 British English 🇬🇧, 2 English Mexican 🇲🇽 , 1 English South African 🇿🇦, and 4 English Australian voices 🇦🇺. Head over to our Library (library.audiostack.ai) to explore and try them all out!
Suggestions to try:
Finch, 11L, US
Elora, 11L GB
Conversational_greg WSL AU
Narration_Issa WSL ZA
Narration_lorenzo WSL MX:
**Stay tuned as there’s more coming in the next month!
**
https://library.audiostack.ai/
We've enhanced our msnr voices with punctuation symbols and respective lengths, as well as enabling break tags. This should add naturalness and enhanced pronunciation, as well as improved speech flow. Some examples:
Full break is 600 milliseconds.
Comma is 300 milliseconds,
Colon is 300 milliseconds:
Semicolon is 400 milliseconds;
Question mark is 400 milliseconds?
Exclamation mark is 600 milliseconds!
Break tag with three seconds
Break tag with thousand millisecond
Break tag with thousand milliseconds using single quote
Break tag with thousand milliseconds using single quote and no space
Special characters are supported again in the API: & and %. These are both normalised for English and German voices!