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 Google model that turns text descriptions into audio. It is suitable for voiceovers for videos, podcasts, educational materials, voice prompts in applications, and quick audio drafts. The context window is 65,536 tokens, so you can submit a long script in its entirety rather than breaking it into small pieces.

According to our data, the model generates audio, but the exact container and bitrate are not specified in the specifications — rely on what the API returns. The output limit is 32,000 tokens per request: this is enough for a long segment, and it is convenient to assemble a large project from several parts.

There is no specific note about reasoning before answering in our data, so we cannot confirm such a mode, but we will not deny it either. The easiest way is to check in practice: run the model in BotHub and compare the result with other models in the same window.

There is no note about function calling and structured JSON output in our data, so we will not claim this. If the capability is critical for integration, connect via the unified OpenAI-compatible BotHub API: the model is changed by one parameter in the request, no need to rewrite code and keys.

Acceptance of anything other than text is not noted in our data, so expect text input and audio output. If you need to work with images or video, other models are available nearby in BotHub — switching takes a couple of seconds in the same interface.

The language of prompts and voiceovers is not described in our data, so we will not promise anything here — it is more reliable to check with your own text. On the service side, we guarantee something else: access from Russia without a VPN or foreign card, payment with Russian cards in rubles, and pay-as-you-go for tokens.