Hi,
I am pleased to introduce speakimo. Speakimo is built on bubble and integrates with Google and MS Azures text to speech. All voices on the app are the latest in current development and are much more human like than the standard voices that many apps generate.
I created Speakimo first off as a tool for me as a video animator to create quality voice overs without the large cost. Speakimo provdes a pay as you go option and you can purchase top up packs for a one off price.
You can sign up for free at
app.speakimo.com
Home Page is speakimo.com
Appreciate any feedback you may have.
2 Likes
Congratulations and well done.
Can I ask the following:
- Do you use any plugins or did you simply use the google api?
- Also, how did you apply the pitch changing of the voices?
- Are you using bubble storage or a plugin such as wasabi for the audio uploads?
Thank you
Of course happy to answer.
-
No plugins used for the google api, I integrated directly with the api. The Azure integration was a little more tricky as I couldn’t call the api directly from Bubble so I had to setup a workflow in integromat.com to process the information and then send that back to Bubble.
-
Pitching changing is built into the Google and Azure api’s so the user selects the pitch front end ( a number) and then its passed through the api request: below is google, Azure is a text parameter.
{
“audioEncoding”: enum (AudioEncoding),
“speakingRate”: number,
"pitch": number,
“volumeGainDb”: number,
“sampleRateHertz”: integer,
“effectsProfileId”: [
string
]
}
- Yes basically the files are all saved to Bubble as they are needed in the workflows and processing. Once the voice file is generated I setup a workflow to save the file to my own S3 storage and then delete the files from Bubble, thus offloading the storage.
Hope this answers your questions, let me know if you need more info.
Thanks
