Saltar al contenido principal

GoogleAdded Apr 20, 2026Text to speechAnonymized

Gemini 3.1 Flash TTS

Gemini 3.1 Flash TTS is Google’s Gemini-based speech model, which follows natural-language instructions for tone and pacing. It offers 30 voices and returns MP3, Opus or WAV audio.

tts-gemini-3-1-flashPOST https://api.venice.ai/api/v1/audio/speech
Per 1M characters
$188
Per minute
$0.1547
≈ 825 characters
Per hour
$9.28
of generated speech
Voices
30
Formats
3
mp3, opus, wav

Pricing

USD per 1M characters
1M characters billed unit
$188
1 minute
$0.1547
≈ 825 characters
1 hour
$9.28
2,000-word article
$2.25
≈ 12K characters

Minute and hour figures assume 150 words per minute.

Voices

Specs

Model ID
tts-gemini-3-1-flash
Endpoint
POST /api/v1/audio/speech
Voices
30
Formats
mp3, opus, wav (default mp3)
Added
Apr 20, 2026
POST/api/v1/audio/speech
curl https://api.venice.ai/api/v1/audio/speech \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tts-gemini-3-1-flash",
"input": "Private AI for everyone.",
"voice": "Achernar",
"response_format": "mp3"
}' --output speech.mp3

Privacy

Tier 1 · this model
Anonymized

Venice hides your identity and stores no prompts. Google still sees the content.

Tier 2
Private

Not available

Tier 3
TEE

Not available

Tier 4
End-to-end encrypted

Not available