Text-to-speech
Read assistant replies aloud, or open the full TTS Studio to craft audio with voice selection, emotion controls, waveform preview, and export. Uses OpenAI Speech API (POST /api/tts).
Credits: 500
Built-in capabilities you can use from the main chat. Most features use your credits and require a configured API key (e.g. OpenAI) on the server.
Read assistant replies aloud, or open the full TTS Studio to craft audio with voice selection, emotion controls, waveform preview, and export. Uses OpenAI Speech API (POST /api/tts).
Create images from prompts in the full Image Studio — canvas-centred layout, 6 style presets, inpaint mode, variation strip, and platform export presets (Shopify, Instagram, Amazon).
Open Image Studio →Attach PDFs in chat for text extraction when the server has OpenAI configured (OCR path in the app).
Open Home →The agent can search the web or news as part of answering your request (when enabled in the workflow).
Open Home →