Review the confirmed Gemini 3.8 Flash-Lite TTS speech scope, plan speaker-based dialogue, and compare audio models that are available on Rivya now.
Example output
No suitable example is available for this model yet.
Best for
Supports
Temporarily unavailable
Rivya cannot safely determine the maximum credit liability before a run starts, so generation remains disabled and no availability date is promised.
Available speech alternatives
Gemini 3.8 Flash-Lite TTS FAQ
No. The published model description defines speakers and ordered dialogue turns, but it does not establish a maximum number of speakers or turns, a total text limit, or a dependable maximum audio-token cost. Rivya therefore keeps generation disabled before credits can be reserved or a run can begin.
The confirmed scope covers text to speech and dialogue to speech, including speaker assignments and sequential spoken turns. This page records that scope for research; it does not expose a runnable prompt form or model controls while the safety check remains unresolved.
The page gives researchers a stable status reference and points to speech models that can be used today. It does not predict when Gemini 3.8 Flash-Lite TTS will become available.
Use the page to understand the confirmed speech and dialogue scope, check Rivya's current availability status, and choose an available alternative. There is no generation form, callable API entry, or pricing offer for this model while it remains unavailable.
Choose ElevenLabs Dialogue V3 for a multi-speaker exchange, ElevenLabs Turbo 2.5 for a fast single-speaker draft, or ElevenLabs Multilingual V2 when cross-language delivery is the priority.
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 multi-speaker dialogue workflow.
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 fast, single-speaker text-to-speech drafts.
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 multilingual narration and localization work.
