You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.

This is a speech synthesis model from Google: it takes text and outputs audio. It is suitable for voicing articles and newsletters, educational materials, voice notifications, assistant responses, and short audio formats. The context window is 65,536 tokens, so you can submit voluminous material in a single request.

Our data only confirms audio generation, so we will not specify concrete formats, sampling rates, or voice sets — these should be checked in the API response. The output limit is 32,000 tokens per request, so it is more convenient to split long text into parts.

A separate reasoning mode for this model is not noted in our data — this is not a denial, we just cannot confirm it. It is usually not needed for speech synthesis: the model works with ready-made text. Move the logic to a text model, and use this one only to voice the result.

There are no notes about function calling or structured JSON output in our data, but we will not deny them either. It is more practical to build a combination: a text model handles tools and structure, while voicing is done via the unified OpenAI-compatible BotHub API — you won't have to rewrite the integration when switching.

Input of such files is not noted in our data: the confirmed scenario is text input and audio output. If the project needs image analysis or transcription, connect a suitable model in the same BotHub window and pass its result here for voicing.

There is no list of supported languages in our data, so we will not promise anything specific about pronunciation — it is more reliable to run your text and listen to the result. BotHub itself is accessible from Russia without a VPN or foreign card, with payment via Russian cards based on actual token usage.