Skip to content
Start free

Text to speechEvery plannewstyle-promptstwo-speaker-dialogue

Gemini 3.8 Flash TTS

Gemini 3.8 Flash TTS: a text to speech model you can use in AutoReel.

At a glance

Category
Text to speech
Produces
audio
Typical run time
~10 s
Plans
Every plan, including Free
Price
Depends on the settings; shown before you generate

Parameters

The settings Gemini 3.8 Flash TTS accepts. In the Studio they appear as a form with sensible defaults; through the API they’re the params of a generation.

textstring
Text to speak. For dialogue, leave text empty and provide speakers and turns. Delivery directions belong in style_instructions.Up to 8000 characters
voicechoice
Prebuilt voice for single-speaker speech.One of: Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Puck, Pulcherrima, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, ZubenelgenubiDefault: Kore
style_instructionsstring
Optional delivery style, tone, pacing, or accent. Included in billable character count.Up to 2000 characters
speakerslist of object
Optional dialogue setup: add exactly two distinct speaker IDs and their voices, then add turns and leave text empty. Omit for single-speaker speech.Up to 2 items
turnslist of object
Optional dialogue turns: add at least one turn and match each speaker_id to the two configured speakers. Leave text empty when using dialogue. Total input must fit 8192 tokens.Up to 100 items

models

Make your first reel free

Sign up and get 100 credits to try every format: AI UGC videos, talking creators, slideshows and hook + demo reels. No card needed.

Start freeSee pricing