Text -to-speech allows you to set up a unique voice for the AI assistant so it can convert written words into speech and communicate with you with its adjustable tone, clarity, and speed like a person.
Step-by-step to set up Text-to-speech on TypingMind
1. Set up Text-to-speech
- Click on the Settings menu on the left panel
- Select Text-to-speech tab to set up a voice for the AI assistant
First you need to choose a Speech API to enable text-to-speech feature, there’re currently 3 options:
- WebSpeech: this option doesn’t require an API key, just choose a voice and start a conversation.
- ElevenLabs: you need to get the API key from ElevenLabs as follows:
- Sign up for ElevenLabs: https://beta.elevenlabs.io
- Click on your profile picture on the top right corner > Profile to get the API key.
- Copy the API Key to TypingMind and click “Check key” to see if the key is working or not.
- The ElevenLabs Text-to-speech provides different speech models that are optimized for different purposes. Please check the details here: https://elevenlabs.io/docs/speech-synthesis/models
Please note that if your usage surpasses the free limit provided by ElevenLabs API, it is necessary to upgrade to a ElevenLabs’ paid plan.
- OpenAI Text-to-speech: use voices from OpenAI. This requires an OpenAI API key that can be entered outside, in the API key box. If you have already entered the API key outside, then there’s no settings needed for this.
2. Start talking!
After you done the setup, you can start a conversation, when you receive the AI response, there will be a Play button right below the answer so you can play the audio for the AI assistant manually.
You can also set “Auto-play” so it can automatically play the audio when the AI response is done generating.
And that’s it, you’re all set.