Models / CartesiaSonic / / Cartesia Sonic-2 API
Cartesia Sonic-2 API
Audio
Low-latency, ultra-realistic voice model, served in partnership with Cartesia.
Try our Cartesia Sonic API
Try this model in our Playground!
Cartesia Sonic-2 API Usage
Endpoint
cartesia/sonic-2
RUN INFERENCE
curl -X POST "https://api.together.xyz/v1/audio/generations" \
-H "Authorization: Bearer $TOGETHER_API_KEY" \
-H "Content-Type: application/json" \
--output speech.mp3 \
-d '{
"model": "cartesia/sonic-2",
"input": "",
"voice": "sweet lady",
"response_encoding": "pcm_f32le",
"response_format": "wav",
"sample_rate": 44100,
"stream": false
}'RUN INFERENCE
from together import Together
client = Together()
response = client.audio.speech.create(
model="cartesia/sonic-2",
input="",
voice="sweet lady",
response_encoding="pcm_f32le",
response_format="wav",
sample_rate=44100,
stream=False
)
response.stream_to_file("speech_file_path.wav")RUN INFERENCE
import Together from "together-ai";
const together = new Together();
const response = await together.audio.speech.create({
model: "cartesia/sonic-2",
input: "",
voice: "sweet lady",
response_encoding: "pcm_f32le",
response_format: "wav",
sample_rate: 44100,
stream: false
});
if (response.body) {
const nodeStream = Readable.from(response.body as ReadableStream);
const fileStream = createWriteStream("./speech.mp3");
nodeStream.pipe(fileStream);
}How to use Cartesia Sonic-2
Model details
Prompting Cartesia Sonic-2
Applications & Use Cases
