Text to Audio (TTS)
Turns text into synthetic voice audio (AI-generated) and sends it straight into the conversation as a voice message. Part of Chat Tools.
How to use
- Type the text (up to 2,000 characters).
- Choose the voice (alloy, ash, ballad, coral, echo, fable, nova (default), onyx, sage, shimmer, verse, marin, cedar).
- Choose a mood — Neutral, Upbeat, Serious, Empathetic, Calm or Sales — which automatically fills in an instruction field (editable, up to 500 characters).
- Click "Generate", listen to the preview and then "Send".
Note
Changing the text, the voice or the mood after generating invalidates the audio — you need to generate it again before sending. The last voice and mood used are saved in the browser for next time.
Warning
This tool uses the OpenAI API key registered in your workspace — you must have one configured. The generation cost is charged by OpenAI itself, outside NicoChat (there is no charge in NicoChat credits here). Sending follows WhatsApp rules — it does not work, for example, if the 24-hour service window has already closed.