Natural multilingual text-to-speech with multiple voices and expressive, human-like prosody.
| NovAI | OpenRouter | Access | |
|---|---|---|---|
| Per 1K characters | $0.013 | N/A | Official direct |
curl https://aiapi-pro.com/v1/audio/speech -H "Authorization: Bearer $NOVAI_API_KEY" -H "Content-Type: application/json" -d '{
"model": "qwen-tts",
"input": "Hello, welcome to NovAI.",
"voice": "Cherry"
}'
import requests
r = requests.post(
"https://aiapi-pro.com/v1/audio/speech",
headers={"Authorization": "Bearer YOUR_NOVAI_API_KEY"},
json={"model": "qwen-tts", "input": "Hello, welcome to NovAI.", "voice": "Cherry"},
)
print(r.json()["audio_url"])
Returns a hosted audio_url (WAV) you can stream or download - just set base_url to https://aiapi-pro.com/v1 and use your NovAI API key. Full reference in the API docs.