voice-memo

To convert text to speech for an audio reply, this Skill processes your input text using a configured TTS provider like ElevenLabs or OpenAI and outputs an OGG Opus audio file. It uses curl and jq to handle the HTTP requests and deliver natural voice memos.

Yes, you can use either ElevenLabs or OpenAI as your text-to-speech provider. You must configure the required API keys for your chosen TTS provider to generate natural-sounding voice memos successfully.

The best way to send a voice memo from a text summary is to use the voice directive in your message. This triggers the text-to-speech conversion, generating a one-paragraph audio memo delivered as a native voice note or audio attachment.

Yes, you need curl and jq installed to generate OGG Opus audio files. These dependencies are required for executing HTTP requests to the TTS provider and handling the JSON responses during the text-to-speech conversion process.

Yes, this text-to-speech tool supports silent mode for background tasks and scheduled memos. This allows you to generate and deliver audio summaries or quick updates without triggering interactive notifications.

The primary limitation is that the voice directive generates a one-paragraph audio memo, making it best suited for quick updates, summaries, or reminders rather than long-form text-to-speech conversion.