Alternative to whisper and extra voices

[ghost]

You can use WebCaptioner for speech recognition its a free website and has a webhook, and can also do english tts voices. via experiments, although it does not do translations but it can subtitle in a variety of languages.

if you look at this project on github
https://github.com/VRCWizard/TTS-Voice-Wizard
you can probably figure out how to get the webhook working as they've done it along with showing other tts voice providers such as Azure Polly Tiktok voices etc.

[hoangvu12]

Does it has API?

[ghost]

it uses the web speech api, which is has its own documents, but since it has webhooks you should be able to work with it from the url, kinda like what TTS voice wizard does already