Gemini 3.8 TTS

Gemini 3.8 TTS (google/gemini-3.8-flash-tts and google/gemini-3.8-flash-lite-tts) — Google speech synthesis: dozens of named voices (Zephyr, Puck, Charon, Kore, Fenrir, Leda, Orus, Aoede and more), natural intonation and pauses. Two tiers: Flash for quality, Flash Lite for price. Billed per 1,000 input characters.

Parameters

Field	Description
model	google/gemini-3.8-flash-tts or google/gemini-3.8-flash-lite-tts
input	Text to speak
voice	A voice from the model’s catalog (see GET /v1/models); defaults to the first
response_format	mp3 (default), wav, opus and others

Prices

Model	Per 1K input characters
gemini-3.8-flash-tts	$0.0301
gemini-3.8-flash-lite-tts	$0.0201

Example

curl https://api.mixen.ai/v1/audio/speech \
  -H "Authorization: Bearer $MIXEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.8-flash-tts",
    "input": "Hi! This is the voice of the Gemini model.",
    "voice": "Kore"
  }' -o speech.mp3

Strengths and limitations

• Named voices — a stable timbre across requests; each model’s voice list is in the catalog.
• Billing by input characters: a long text has a predictable price; audio duration is not measured.
• The voices are tuned for English speech; Russian is read with an accent — for natural Russian prefer MiniMax Speech.

All models — in the catalog. The full synthesis workflow — guide.