Ask a Question

Question about Voices and Availability

Hello, on the pricing page (https://www.aflorithmic.ai/pricing) it shows 350+ voices for INDIE and all higher plans (just not the free version). We’re currently using INDIE plan and some voices show in the API as premium. Can you advise on why some voices aren’t available?

Mood API

Hello, I’m wondering if there are plans in the future to add a mood or emotion to sections so that audio text to speech might have a mood assigned like “scared” or “angry” or “happy” etc?

Mastering/Mixing Uploaded Audio Files

Hello, is it possible to upload audio files and master them in conjunction with synthetic speech files. For example, create audio from a script and then master it with an audio file we uploaded to create one file.

Any way to add a pause in the middle of text

Is there any way to add a pause for the Text to Speech. Something like "In this sentence I want the voice to pause for 2 seconds here,, is there anyway to do that". So this doesn't work but didn't know if there's a way to add some pauses in the middle of text by inserting characters or something. didn't see anything in API about it.


Question about voice cloning. How much has to be recorded to clone a voice?

Can i edit the title of a Question after posting?

Hello, Currently, I can edit the description of a question once I am done posting it. But is it possible to edit the Title of the question after posting? Thanks.

Speakers for some languages

Hello, I am trying to create speech with different speakers from different languages and noticed that some of them are not working. Eg: I am not able to run my script with the speakers from the language "Telugu", but the same script works with other speakers in the main dashboard. Is this a work in progress or a bug? Thanks.

Voice Pitch

I wanted to change the pitch of a voice character, is it possible? Is there also a list of specific voice effects that are currently available?

API call to delete Script ?

Is there one??


Is there any visual sandbox, playground or any other form of playing with the voices prior to sending API requests? Thanks, Yuri