Write text in the editor and automatically convert into audio using the speaker voice | Voters

Write text in the editor and automatically convert into audio using the speaker voice

Armel Beaudry Kembe Tchemeube

November 12, 2022

Santé Quantique

Any update on that one? Thanks

Charles Draven

Here are some options to explore:
https://murf.ai/text-to-speech-api
https://docs.app.resemble.ai/docs/resource_voice/create

Armel Beaudry Kembe Tchemeube

Charles Draven: I just saw your message. Thank you for taking the time to share those options. I have reached out to Resemble AI a few months ago and they told me their API was not ready for that use case. I have reached out to Murf after reading your suggestion. We will see how it goes :)

Charles Draven

Armel Beaudry Kembe Tchemeube: Great! The other approach is chaining outputs from TTS APIs that have a character limit, or use batch synthesis: https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/batch-synthesis

Ida Ma

To solve this issue properly, you probably need to solve the issue of voice cloning. Please Check Descript and see how they solve the voice cloning issue, 11 labs is also good but too expensive. https://beta.elevenlabs.io/

Armel Beaudry Kembe Tchemeube

Ida Ma: Unfortunately, the technology to solve voice cloning is not trivial. That is why only a few companies offer it. I have reached out to Elevenlabs to talk about their offering and see it can be used to solve this problem at scale. I will keep you in the loop. Thank you for suggesting them as I was not aware of them

Nick R

For a few choices to integrate with the app, just Google: voice cloning api

Armel Beaudry Kembe Tchemeube

Nick R: thank you for the recommendation. I have looked into it already but it is difficult to find something that works reliably and at scale. If you know any API that is, let me know

Sebastien R

Armel Beaudry Kembe Tchemeube is this still being considered? 2 years later there seems to be more options now, including elevenlabs