Loading models
Loading models
Loading model
Loading model
Kokoro 82M is good. These would like a word anyway.
Lightweight 82M parameter TTS model based on StyleTTS2. The most popular text-to-speech model on Replicate with over 78 million runs. Known for natural-sounding speech with low latency.
from openai import OpenAI
client = OpenAI(
base_url="https://api.deepinfra.com/v1/openai",
api_key="$DEEPINFRA_TOKEN",
)
response = client.chat.completions.create(
model="hexgrad/Kokoro-82M",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.deepinfra.com/v1/openai",
apiKey: process.env.DEEPINFRA_TOKEN,
});
const response = await client.chat.completions.create({
model: "hexgrad/Kokoro-82M",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);curl https://api.deepinfra.com/v1/openai/chat/completions \
-H "Authorization: Bearer $DEEPINFRA_TOKEN" \
-H "Content-Type: application/json" \
-d '{"model":"hexgrad/Kokoro-82M","messages":[{"role":"user","content":"Hello!"}]}'Set DEEPINFRA_TOKEN with your DeepInfra API key from deepinfra.com/dash/api_keys.
6 outputs · generated before accounting joined the chat