While the Open AI TTS is great, it doesn't do many accents and, for localisation purposes, I'd prefer integrating Elevenlabs' voices.
With my limited experience with APIs (I consider myself a nocoder), I tried creating an API block that carries out a POST request to the Elevenlabs tts streaming endpoint. It returns a data object that is a long string of characters but not a url, which is what I believe we need to pass to the audio file block.
I tried searching more about this in this discord and in the docs but without success. If anyone has any particular tips or steps, would be appreciated.
I don't have a tutorial on this one, but I did try Eleven labs a while ago. If I remember correctly, I wasn't able to stream the audio response into Typebot but rather had to save the response as a file, capture it in the Audio Block, and then the user would have to click on play to hear the audio.
Thanks, Nefer. I’m away from my computer right now so can’t share screenshots, but could you explain how to go from the POST request results to the audio block? (Excuse my noobishness, I don’t consider myself a coder but am learning more about APIs).
If you do plan that, that would be wonderful. The use case I see for it is especially in international markets where the existing Open AI TTS English audio returned doesn't match the customer rep avatar in, say, the Middle East. English accents or cloned voices would really help with personalising that experience.
