For narration or dialogue projects, compare the available speech models below. Gemini 2.5 Pro TTS remains paused on Rivya, with no script submission or voice controls.
Temporarily unavailable
Rivya has not confirmed the maximum audio-output token usage for a task. It needs that bound to reserve enough credits before generation starts.
Available speech models to compare
Model examples
Review examples to help decide whether the model fits your task.
Model strengths
Model strengths
Gemini 2.5 Pro TTS FAQ
No. Gemini 2.5 Pro TTS is temporarily unavailable on Rivya, including the model page, Studio and Public API. Its listing describes a speech model, but no generation request can start here.
Rivya has not established a reliable upper limit for a task's audio-output token usage. Without that bound, it cannot reserve enough credits before generation starts. Submission remains disabled.
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
Use ElevenLabs Dialogue V3 for scripts with separate speaker turns.
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
Compare ElevenLabs Multilingual V2 for single-speaker speech from your script.
Example output
Gemini 2.5 Pro TTS
Example output
Gemini 2.5 Pro TTS
Best for
Supports
This section of the garden brings together plants that thrive in dry soil. Lavender attracts pollinators, and the low stone wall stores warmth after sunset.
Keep a photo of your booking details offline. Check the last bus time before leaving the station, and carry enough water for the walk to the viewpoint.
Suggested uses
Tasks to consider
Model details
Provider
Category
Audio
Rivya has not announced an activation date. This is a listed speech model under a temporary availability restriction; check its status before planning a run.
This page has no script field, voice or language controls, model settings or credit quote while the model is paused. It cannot be called through Rivya's API or start a new audio task that adds a result to History.
Use ElevenLabs Dialogue V3 for scripts with separate speaker turns. Compare ElevenLabs Multilingual V2 and ElevenLabs Turbo 2.5 for single-speaker narration. Check each model's voices, language behavior and credit estimate before submitting.
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
Compare ElevenLabs Turbo 2.5 for a single-speaker narration draft.
