Gradium TTS
Gradium TTS is Gradium’s text-to-speech model for natural, low-latency voice generation. It offers 12 voices and returns WAV, PCM or Opus audio.
Per 1M characters
$47.50
Per minute
$0.0392
≈ 825 characters
Per hour
$2.35
of generated speech
Voices
12
Formats
3
wav, pcm, opus
Pricing
USD per 1M characters1M characters billed unit
$47.50
1 minute
$0.0392
≈ 825 characters
1 hour
$2.35
2,000-word article
$0.57
≈ 12K characters
Minute and hour figures assume 150 words per minute.
Voices
Specs
- Model ID
tts-gradium-v1- Endpoint
POST /api/v1/audio/speech- Voices
- 12
- Formats
- wav, pcm, opus (default wav)
- Added
- Jun 5, 2026
POST
/api/v1/audio/speechcurl https://api.venice.ai/api/v1/audio/speech \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tts-gradium-v1",
"input": "Private AI for everyone.",
"voice": "Alice",
"response_format": "mp3"
}' --output speech.mp3Privacy
Tier 1 · this model
Anonymized
Venice hides your identity and stores no prompts. Gradium still sees the content.
Tier 2
Private
Not available
Tier 3
TEE
Not available
Tier 4
End-to-end encrypted
Not available