Gemini 3.8 Flash TTS

google/gemini-3.8-flash-tts

A text-to-speech model, at $1.05 per million characters.

Details

Maker: google
Kind: Speech
Price: $1.05 per million characters
Capabilities: None listed
Takes: Text
Returns: Audio
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-09-23

Description

Gemini 3.8 Flash TTS is Google's preview text-to-speech model for expressive narration and multi-speaker dialogue in 130 languages. It supports line-by-line style direction, regional accents, streaming synthesis, and consistent long-form audio. Prebuilt and curated voices, voice design, and voice replication help creators produce audiobooks, studio narration, games, and podcasts.

Call it

curl

curl https://phantom.codes/v1/audio/speech \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.8-flash-tts",
    "input": "Hello from Phantom"
  }' \
  --output speech.mp3

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model