> ## Documentation Index
> Fetch the complete documentation index at: https://veniceai-feat-models-redesign.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Gradium TTS API
> Gradium TTS API on Venice: text to speech with 12 voices at $47.50 per 1M characters (about $0.039 per minute). Anonymized access without your identity.
export const HubMount = ({view, children, ...props}) => {
const [hub, setHub] = useState(null);
const [failed, setFailed] = useState(false);
useEffect(() => {
let alive = true;
const w = window;
if (!w.__veniceModelHub) {
const urls = w.location.hostname === 'localhost' ? ['http://localhost:3333/data/model-hub.bundle.json', '/data/model-hub.bundle.json'] : ['/data/model-hub.bundle.json'];
const load = i => fetch(urls[i], {
cache: 'no-cache'
}).then(res => {
if (!res.ok) throw new Error(`bundle ${res.status}`);
return res.json();
}).catch(err => i + 1 < urls.length ? load(i + 1) : Promise.reject(err));
const Frag = <>.type;
const h = (type, props, ...kids) => {
const T = type;
const {key, ...rest} = props || ({});
if (!kids.length) return ;
if (kids.length === 1) return {kids[0]};
return {kids.map((kid, i) => {kid})};
};
w.__veniceModelHub = load(0).then(bundle => new Function(`return (${bundle.code})`)()({
h,
Fragment: Frag,
useState,
useEffect,
useRef,
useMemo,
useCallback
}));
}
w.__veniceModelHub.then(instance => {
if (alive) setHub(instance);
}).catch(() => {
w.__veniceModelHub = null;
if (alive) setFailed(true);
});
return () => {
alive = false;
};
}, []);
const View = hub ? hub[view] : null;
if (View) return {children};
if (failed) {
return
The interactive model catalog could not load. The full data is below.
{children}
;
}
return
{children}
;
};
# Gradium TTS API
Gradium TTS is a text-to-speech model by Gradium, available on the Venice API as `tts-gradium-v1`. Requests are anonymized, so the provider never sees your identity.
## Gradium TTS API pricing
| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `tts-gradium-v1` | Standard | Anonymized | \$47.50 per 1M characters |
## Gradium TTS specifications
| Spec | Value |
| - | - |
| Provider | Gradium |
| Released | Jun 5, 2026 |
| Privacy | Anonymized |
| Voices | 12 |
| Formats | wav, pcm, opus |
## How to use the Gradium TTS API
Send requests to `POST https://api.venice.ai/api/v1/audio/speech` with `"model": "tts-gradium-v1"` and your API key.
```bash theme={null}
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": "mp3"
}' --output speech.mp3
```
## Gradium TTS API FAQ
### How much does the Gradium TTS API cost?
$47.50 per 1M characters of input text, about $0.039 per minute of generated speech. Prices are in USD and can be paid in DIEM at parity.
### What is the Gradium TTS model ID?
Use `tts-gradium-v1` as the `model` parameter.
### Is the Gradium TTS API private?
Gradium TTS is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.
### How many voices does Gradium TTS have?
12 voices, for example `Alice`, `Davi`, `Elise`. Output formats: wav, pcm, opus.
### Which endpoint does the Gradium TTS API use?
Call `POST /audio/speech`.
## Related models
* [Chatterbox HD (Resemble AI) API](/models/chatterbox-hd): \$50.00 per 1M characters
* [ElevenLabs Turbo v2.5 API](/models/elevenlabs-turbo-v2-5): \$62.50 per 1M characters
* [Orpheus TTS API](/models/orpheus-tts): \$62.50 per 1M characters
* [Qwen 3 TTS 0.6B API](/models/qwen-3-tts-0-6b): \$87.50 per 1M characters
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.