Custom Text-to-Speech integration using MiniMax API (speech-02-turbo and newer models) via WebSocket for minimal latency.
I previously used ElevenLabs for many months, but they don't allow cloning of any voice (e.g., a famous person's voice), so I looked for an alternative and MiniMax Audio met my requirements. There was no Home Assistant integration, so I wrote my own.
- speech-2.8-hd
- speech-2.6-hd
- speech-2.8-turbo
- speech-2.6-turbo
- speech-02-hd
- speech-02-turbo
- Open HACS -> Integrations.
- Click the menu (three dots) in the top right corner -> Custom repositories.
- Paste this repository's URL.
- Select the Integration category.
- Click Add, then install "MiniMax TTS".
- Restart Home Assistant.
Go to Settings -> Devices and Services -> Create Integration and search for MiniMax TTS. You will need:
- API Key: From the MiniMax Console https://platform.minimax.io/user-center/basic-information/interface-key -> Create new secret key
- Voice ID: E.g.,
male-qn-qingse: Three dots on the end of voice row -> Copy Voice ID
If you find this integration useful, you can support my work by buying me a coffee: