This page covers various techniques when using HyperTTS. Starting from scratch ? Take a look at our our HyperTTS tutorial for beginners
Use the ElevenLabsCustom service to use your own ElevenLabs API key, for custom voices and free tier
How to add Furigana hints when generating Japanese audio with HyperTTS
What are the free services available to create audio ?
Realtime voices don't sound the same when reviewing on iPhone or Android, but you can customize them
If you want to replace an HTML tag in a particular way, you can add a replacement rule
You can add pauses in the audio before, after, or in the middle
You only want to add audio to the notes which don't already have an audio file in them. You can use Anki's card browser queries.
Some services support SSML and this allows you to tweak the pronunciation if the default TTS output is not correct.
When troubleshooting a complex issue, you can turn on debug logging to a file.
Advanced mode lets you set up automated rules which will run automatically or manually for certain notes. This lets you add multiple audio files to one note with one click.
The simplest method of adding audio, one note at a time.
All the ways of adding audio, find the one which suits you the best.
How to generate an alternate pronunciation for Chinese text, if the default TTS output wasn't correct.
Can't find what you're looking for ? Please email help@mail.vocab.ai or chat with us and I'll try to help you out as soon as possible.