Audio scene
Historical audio examples for illustration. They do not demonstrate the current single-speaker, short-script mode and are not ready-to-submit prompts.
Enter your script, choose a preset voice, and generate one audio segment. When the task succeeds, you can listen to or download the WAV file.
The final cost is rounded up to whole credits.
Example output
Historical audio examples for illustration. They do not demonstrate the current single-speaker, short-script mode and are not ready-to-submit prompts.
Text to Speech
Example output
Historical audio examples for illustration. They do not demonstrate the current single-speaker, short-script mode and are not ready-to-submit prompts.
Best for
Supports
Try this model
No results to display yet.
Model examples
Review examples to help decide whether the model fits your task.
Historical audio examples for illustration. They do not demonstrate the current single-speaker, short-script mode and are not ready-to-submit prompts.
Historical audio examples for illustration. They do not demonstrate the current single-speaker, short-script mode and are not ready-to-submit prompts.
Historical audio examples for illustration. They do not demonstrate the current single-speaker, short-script mode and are not ready-to-submit prompts.
Benvenuti al laboratorio. Prima di iniziare, controllate gli strumenti e lasciate libero il passaggio vicino alla porta. Historical audio examples for illustration. They do not demonstrate the current single-speaker, short-script mode and are not ready-to-submit prompts.
Historical audio examples for illustration. They do not demonstrate the current single-speaker, short-script mode and are not ready-to-submit prompts.
Toast the spices in a dry pan for thirty seconds. Stir in the tomatoes, lower the heat, and simmer until the sauce becomes thick enough to coat a spoon. Historical audio examples for illustration. They do not demonstrate the current single-speaker, short-script mode and are not ready-to-submit prompts.
Model strengths
Model strengths
Suggested uses
Tasks to consider
Model details
Provider
Category
Audio
Capabilities
Text to Speech
Credit charges
Rivya reserves 22 credits before submission. Confirmed lower usage returns the difference. Unconfirmed charges remain reserved for review.
Inputs
Prompt only
Prompt requirements
Up to 1,024 UTF-8 bytes
Developer access
Use Gemini 3.8 Flash TTS through Public API v1. Check the model reference for supported inputs, parameters, and credit charges before sending a request.
Gemini 3.8 Flash TTS FAQ
This form reads one text segment aloud in one preset voice. Multi-speaker dialogue, voice cloning, attachments, and custom voice descriptions are unavailable here.
Enter up to 1024 UTF-8 bytes. The byte counter includes spaces and line breaks; it is not a character count. Your text is sent as entered.
Rivya reserves 22 credits before submitting the task. If confirmed usage is lower, the difference is returned. Missing, invalid, or higher charges remain under review; they do not trigger an automatic new generation.
Listen to the audio or download the WAV file. If submission is uncertain, check the existing task in your history before starting another generation.
Compare alternatives
Generate audio from a dialogue script on Rivya, with a preset voice selected for each line. Set Stability and an optional language code for the request.
Why consider it
Input option: Dialogue script + voice settings
Turn written scripts into spoken audio with ElevenLabs Turbo 2.5 on Rivya. Choose a preset voice and adjust delivery for demos, walkthroughs, and narration.
Why consider it
Credit charges: Rate: 6 credits per 1,000 characters in the main script. Each initial reserve is rounded up, with a minimum of 1 credit.
Generate speech from written scripts with ElevenLabs Multilingual V2. Choose a voice preset and adjust delivery for localized demos, lessons, and narration.
Why consider it
Credit charges: Rate: 12 credits per 1,000 main-script characters. The initial reserve is rounded up to whole credits, with a minimum of 1 credit.