20% off all GPT ๐ŸŽ‰ 30% off DeepSeekLearn more

Gemini 3.8 Flash-Lite TTS

Speech
google/gemini-3.8-flash-lite-tts
CompareGet started
Available Providers
Vertex
Supported Protocols
openai

Providers

Vertex
Input Tokens
$0.5/M
Output Tokens
$6/M
Output Audio
$6/M
Protocols
openai/v1/audio/speech

Code Examples

from openai import OpenAI


client = OpenAI(base_url="https://api.ofox.run/v1", api_key="YOUR_OFOX_API_KEY")
response = client.audio.speech.create(
    model="google/gemini-3.8-flash-lite-tts",
    voice="Kore",
    input="Hello from OFOX.",
    response_format="wav",
    speed=1.1,
    extra_body={"language_code": "en-US", "instructions": "Speak warmly and clearly."},
)
response.stream_to_file("speech.wav")

Gemini 3.8 TTS: language_code and instructions are optional; speed gives an approximate pace. WAV and PCM are fixed at 24 kHz; ฮผ-law and A-law at 8 kHz. SSE defaults to PCM chunks; explicit WAV is assembled into one complete file.

response_format
wav (24 kHz), pcm (24 kHz), ulaw (8 kHz), alaw (8 kHz)

Related Models

More from Google

Google: Gemini 3.8 Flash
$1.5/M/$7.5/M
Google: Gemini 3.7 Flash
$1.5/M/$7.5/M
Google: Gemini 3.5 Flash Lite
$0.3/M/$2.5/M

Similar Models

ElevenLabs Eleven v4
$0.08/1K chars
Gemini 2.5 Flash Lite Preview TTS
$0.5/M / $10/M
Gemini 2.5 Flash TTS
$0.5/M / $10/M

Frequently Asked Questions

Simply set your base URL to https://api.ofox.run/v1 and use your Ofox API key. The API is OpenAI-compatible โ€” just change the base URL and API key in your existing code.