Medusa/modules/Text to Speech
Text to Speech
Turns text into MP3 files and reads a voice channel's chat out loud.
Text to Speech makes audio from text in two ways: as an MP3 file posted in chat, or spoken live in a voice channel.
Audio Files
/tts convert posts the text as an MP3 attachment. Pick a voice, or leave it empty to use the Default Voice.
Voice Narration
/tts voice join brings Medusa into your voice channel. It reads every message sent in that voice channel's text chat out loud. When a new member speaks, it says their name first, then reads their messages without repeating the name until someone else talks.
Narration plays through Discord directly and does not need Lavalink.
Voices
English (US), English (UK), Spanish, French, German, Italian, Japanese, Korean, Chinese, Portuguese and Russian.
Settings
| Setting | Default | What it does |
|---|---|---|
| Default Voice | English (US) | Voice used when none is picked. |
| Maximum Speech Character Length | 200 | Longest text that will be spoken. |
Commands
| Command | What it does |
|---|---|
/tts convert <text> [voice] | Post the text as an MP3 file. |
/tts voice join [voice] | Join your voice channel and start reading its chat. |
/tts voice leave | Leave and stop reading. |
/tts voice status | Show the channel, voice and queue. |
| Speak Message | Right-click a message, then Apps > Speak Message, to get it as an MP3. Off by default on the Commands page. |