Gemini 3.8 Flash TTS - Ekly API

Google’s flagship creative voice: studio-grade acting in 130 languages, two-speaker dialogue with natural back-and-forth, and 30 studio voices plus a library of more than 2,000. Direct each line with a short delivery note such as “whispered, nervous”; add moments like <laugh> or <short pause> right in the text.


Model id	`gemini-3.8-flash-tts`
Media	audio
Submit to	`POST /v1/audio`
Price	0.0275 credits per 1,000 input tokens + 0.495 credits per 1,000 output tokens before discounts
Typical time	about 8.0 s

Request

Required: text
Optional: delivery, voice_name

{
  "model": "gemini-3.8-flash-tts",
  "text": "Did you hear that? <short pause> Something is moving out there.",
  "voice_name": "Zephyr"
}

Field	Allowed	Default
`delivery`	text
`voice_name`	`Zephyr`, `Puck`, `Charon`, `Kore`, `Fenrir`, `Leda`, `Orus`, `Aoede`, `Callirrhoe`, `Autonoe`, `Enceladus`, `Iapetus` …	`"Zephyr"`

Reference inputs take asset ids from POST /v1/uploads or an earlier output’s asset_id. Prices and allowed values come from the live catalog; GET /v1/models/gemini-3.8-flash-tts is always current.