Use this status page to evaluate Gemini 2.5 Pro TTS for narration and cast-script plans, then move to a speech model that is available on Rivya today.
Example output
Gemini 2.5 Pro TTS
Example output
Gemini 2.5 Pro TTS
Best for
Supports
Temporarily unavailable
Generation stays disabled because Rivya cannot yet guarantee a safe maximum credit reservation for every allowed script shape.
Available models for your voice workflow
Gemini 2.5 Pro TTS FAQ
The model is publicly listed for text to speech and dialogue to speech, with structured speaker and dialogue information. Rivya also confirms that it is temporarily unavailable here: this page is for status research and alternatives, not generation.
The published limits do not establish a maximum number of speaker or dialogue entries, a total script limit, or a dependable upper bound for audio-token output. Without that bound, Rivya cannot guarantee a sufficient credit reservation before a task starts, so every generation path remains disabled.
No. It is a documented model under a temporary Rivya availability restriction. Rivya does not publish an activation date on this page.
No. This page explains the current status and helps you compare alternatives. It does not expose model parameters, a generation form, callable API access, or a pricing offer.
Use ElevenLabs Dialogue V3 for a cast conversation, ElevenLabs Multilingual V2 for localized voice delivery, or ElevenLabs Turbo 2.5 when a quick single-speaker draft is the main goal.
Compare alternatives
ElevenLabs' multi-speaker dialogue model on Rivya. It is built for role-based speech generation, with individual voice assignments, stability controls, and dialogue-ready pacing for podcasts, interviews, and character scenes.
Why consider it
Use ElevenLabs Dialogue V3 for an available cast or multi-speaker conversation workflow.
ElevenLabs' multilingual text-to-speech model on Rivya, supporting about 30 languages with auto-detection. It is the stronger option for localization, cross-language delivery, and more natural multilingual voiceovers.
Why consider it
Use ElevenLabs Multilingual V2 for available localization and cross-language voice delivery.
ElevenLabs' fast text-to-speech model on Rivya. With low-latency voice generation and adjustable stability, similarity, style, and speed, it is built for rapid voiceover drafts and interactive TTS projects.
Why consider it
Use ElevenLabs Turbo 2.5 for available rapid single-speaker narration drafts.
