GradiumJun 5, 2026
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.
$47.50
per 1M characters
$2.35
per hour of speech
12
voices
12 voices
Names are case-sensitive. Pick one to use it in the request below.
Capabilities
Formats
wav · pcm · opus, wav by defaultStreaming
streaming: trueOpenAI-compatible
client.audio.speech.create()Pricing
Billed per 1M characters of input, in USD.
Input$47.50per 1M characters
Speech, about$0.0392per minute
Speech, about$2.35per hour
Estimated at 825 characters a minute, about 150 spoken words.
Specs
- Model ID
tts-gradium-v1- Endpoint
POST /api/v1/audio/speech- Voices
- 12
- Formats
- wav, pcm, opus · default wav
- Input
- Up to 4,096 characters per request
- Streaming
- Yes
- Voice cloning
- No
- Privacy
- Anonymized
- Weights
- Closed
- Added
- Jun 5, 2026
Compare
Every text-to-speech model on Venice, cheapest first.
| Model | Voices | Per 1M characters |
|---|---|---|
| Kokoro Text to Speech | 54 | $3.50 |
| Inworld TTS-1.5 Max | 14 | $12.50 |
| xAI TTS v1 | 26 | $18.75 |
| ElevenLabs TTS v4 Turbo | 20 | $46.00 |
| Gradium TTS | 12 | $47.50 |
| Chatterbox HD (Resemble AI) | 9 | $50.00 |
| ElevenLabs Turbo v2.5 | 21 | $62.50 |
| Orpheus TTS | 8 | $62.50 |
| Qwen 3 TTS 0.6B | 9 | $87.50 |
| ElevenLabs TTS v4 | 20 | $92.00 |
| Qwen 3 TTS 1.7B | 9 | $113 |
| ElevenLabs Multilingual v2 | 20 | $115 |
| ElevenLabs TTS v3 | 20 | $115 |
| MiniMax Speech-02 HD | 15 | $125 |
| Gemini 3.1 Flash TTS | 30 | $188 |
Quickstart
OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.
curl 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": "wav"
}' --output speech.wavBase URL
https://api.venice.ai/api/v1Parameters
| Parameter | Values |
|---|---|
model | tts-gradium-v1 |
input | Up to 4,096 characters |
voice | 12 voices |
response_format | wav | pcm | opus |
speed | 0.25 – 4.0 |
streaming | true | false |