Google TTS Standard
Neural Network
Specifications
- Input
- text
- Output
- audio
- Number of voices
- 1
Prompt cost
(per 1M tokens)
How it works Google TTS Standard?
Frequently asked questions about Google TTS Standard
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.
Google TTS Standard is a speech synthesis model: it turns provided text into a ready-made audio track. It is suitable for voiceovers for videos and courses, voice notifications, audio versions of articles, and prototypes of voice services. In BotHub, the model is available from Russia without a VPN or foreign card, with payment in rubles.
The output is synthesized speech — audio that can be immediately taken for editing or sent to an application. Specific parameters depend on your request and synthesis settings, so it is easiest to run a short text fragment and listen to the result before doing a large voiceover.
A separate reasoning mode is not noted in our data: this is a voiceover model, not an analyst. Prepare the logic, structure, and wording of the script in advance — for example, in a BotHub text model, and Google TTS Standard will then voice the finished text in the same window.
In our data, function calling and structured JSON output are not noted for this model — its task is to accept text and output sound. If you need function calling, place a text model alongside it: the unified OpenAI-compatible BotHub API allows you to combine them without rewriting the integration.
Accepting files other than text is not noted in our data: the main scenario is that you provide text and receive a voiceover. For speech recognition, image analysis, or video analysis, connect a specialized model in the same BotHub interface and assemble a single pipeline from the steps.
The model works with the text you provide, but there is no detailed information about the set of synthesis languages in our data. It is more reliable to check with your own material: send a short paragraph, listen to the pronunciation, stress, and intonation, and then launch the voiceover for the entire project.