Repository files navigation

The OpenAI TTS component for Home Assistant makes it possible to use the OpenAI API to generate spoken audio from text. This can be used in automations, assistants, scripts, or any other component that supports TTS within Home Assistant.

• Text-to-Speech conversion using OpenAI's API
• Support for multiple languages and voices – No special configuration needed; the AI model auto-recognizes the language.
• Customizable speech model –Check supported voices and models.
• Integration with Home Assistant – Works seamlessly with assistants, automations, and scripts.
• Custom endpoint option – Allows you to use your own OpenAI compatible API endpoint.
• Chime option – Useful for announcements on speakers.(See Devices → OpenAI TTS → CONFIGURE button)
• User-configurable chime sounds – Drop your own chime sound intoconfig/custom_components/openai_tts/chime folder (MP3).
• Audio normalization option – Uses more CPU but improves audio clarity on mobile phones and small speakers.(See Devices → OpenAI TTS → CONFIGURE button)
• ⭐(New!)Support for new gpt-4o-mini-tts model – A fast and powerful language model.
• ⭐(New!)Text-to-Speech Instructions option – Instruct the text-to-speech model to speak in a specific way (only works with newest gpt-4o-mini-tts model).OpenAI new generation audio models

visit: (https://platform.openai.com/docs/pricing)

service: tts.speaktarget:  entity_id: tts.openai_nova_enginedata:  cache: true  media_player_entity_id: media_player.bedroom_speaker  message: My speech has improved now!  options:    chime: true                          # Enable or disable the chime    chime_sound: signal2                 # Name of the file in the chime directory, without .mp3 extension    instructions: "Speak like a pirate"  # Instructions for text-to-speach model on how to speak

1. Go to the sidebar HACS menu

2. Click on the 3-dot overflow menu in the upper right and select the "Custom Repositories" item.

3. Copy/pastehttps://github.com/sfortis/openai_tts into the "Repository" textbox and select "Integration" for the category entry.

4. Click on "Add" to add the custom repository.

5. You can then click on the "OpenAI TTS Speech Services" repository entry and download it. Restart Home Assistant to apply the component.

6. Add the integration via UI, provide API key and select required model and voice. Multiple instances may be configured.

1. Ensure you have acustom_components folder within your Home Assistant configuration directory.

2. Inside thecustom_components folder, create a new folder namedopenai_tts.

3. Place the repo files insideopenai_tts folder.

4. Restart Home Assistant

5. Add the integration via UI, provide API key and select required model and voice. Multiple instances may be configured.