In Review

In Progress

Completed

Roadmap

Multi-language voices support specifying multiple voices and their corresponding text for each part. Example: ```[S1] Welcome to Art &amp; Crime, where we unravel the boldest art heists in history. [S2] Today, we're with art crime expert Dr Alex Corbin. ```

Generate multi-voice audio in a single generation

hidden

Add a referral system to earn free credits.Please comment below on how you would like to earn credits. For example, if someone joins using your referral link and makes a payment of any amount, how many credits do you think is fair?

Referral system

Hi team, It will be great to add API for this service. Please advice when it will be ready?

High Priority

Real-time voice call ;)

Hi, I enjoy what you guys are building over here, and I want to support it. I’ve had fun creating some voice lines, and when I hit the limit I bought the starter pack to keep going. However, 3 hours have passed since I bought it, and I’m still getting the error “Third-party API Quota exceeded (429)” when I try to generate anything. Should probably be updated more often so paid customers don’t get discouraged. I wish you the best of luck, and hope this gets updated soon. Cheers!

Update API refresh rate

Currently, the voice cloning works only with English text

Multi-language voice cloning

pierre, amelie, marierequires deploying a new model

languages

Add French voices

jana, thomas, maxRequires deploying a model

Add German voices

Model options<ul><li><a target="_blank" rel="noopener noreferrer nofollow" class="link" href="https://replicate.com/kjjk10/llasa-3b-long">https://replicate.com/kjjk10/llasa-3b-long</a></li></ul>Ideally with Orpheus TTS, as to be able to support emotion tags (i.e. <code>&lt;laugh&gt;</code>)

Model options<ul><li>https://replicate.com/kjjk10/llasa-3b-long</li></ul>

SexyVoice.ai

Roadmap