from together import Together
client = Together()

response = client.audio.speech.create(
    model="canopylabs/orpheus-3b-0.1-ft",
    input="Today is a wonderful day to build something people love!",
    voice="tara",
    response_format="mp3",
)
response.stream_to_file("speech.mp3")

import Together from "together-ai";
import { Readable } from "stream";
import { createWriteStream } from "fs";

const together = new Together();

async function generateAudio() {
  const res = await together.audio.create({
    input: "Today is a wonderful day to build something people love!",
    voice: "tara",
    response_format: "mp3",
    sample_rate: 44100,
    stream: false,
    model: "canopylabs/orpheus-3b-0.1-ft",
  });

  if (res.body) {
    const nodeStream = Readable.from(res.body as ReadableStream);
    const fileStream = createWriteStream("./speech.mp3");
    nodeStream.pipe(fileStream);
  }
}

generateAudio();

curl -X POST "https://api.together.xyz/v1/audio/speech" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"canopylabs/orpheus-3b-0.1-ft","input":"Hello world","voice":"tara","response_format":"mp3"}' \
  --output speech.mp3

response = client.audio.speech.create(
    model="canopylabs/orpheus-3b-0.1-ft",
    input="The quick brown fox jumps over the lazy dog",
    voice="tara",
    stream=True,
    response_format="raw",
    response_encoding="pcm_s16le",
)
response.stream_to_file("speech.wav", response_format="wav")

import Together from "together-ai";

const together = new Together();

async function streamAudio() {
  const response = await together.audio.speech.create({
    model: "canopylabs/orpheus-3b-0.1-ft",
    input: "The quick brown fox jumps over the lazy dog",
    voice: "tara",
    stream: true,
    response_format: "raw",
    response_encoding: "pcm_s16le",
  });

  const chunks = [];
  for await (const chunk of response) {
    chunks.push(chunk);
  }

  console.log("Streaming complete!");
}

streamAudio();

import asyncio, websockets, json, base64

async def generate_speech():
    url = "wss://api.together.ai/v1/audio/speech/websocket?model=hexgrad/Kokoro-82M&voice=af_alloy"
    headers = {"Authorization": f"Bearer {api_key}"}

    async with websockets.connect(url, additional_headers=headers) as ws:
        session = json.loads(await ws.recv())
        await ws.send(json.dumps({"type": "input_text_buffer.append", "text": "Hello!"}))
        await ws.send(json.dumps({"type": "input_text_buffer.commit"}))

        audio_data = bytearray()
        async for msg in ws:
            data = json.loads(msg)
            if data["type"] == "conversation.item.audio_output.delta":
                audio_data.extend(base64.b64decode(data["delta"]))
            elif data["type"] == "conversation.item.audio_output.done":
                break

response = client.audio.voices.list()
for model_voices in response.data:
    print(f"Model: {model_voices.model}")
    for voice in model_voices.voices:
        print(f"  - {voice.name}")

response = client.audio.transcriptions.create(
    model="openai/whisper-large-v3",
    file=open("audio.mp3", "rb"),
)
print(response.text)

import Together from "together-ai";

const together = new Together();

const transcription = await together.audio.transcriptions.create({
  file: "path/to/audio.mp3",
  model: "openai/whisper-large-v3",
  language: "en",
});
console.log(transcription.text);

curl -X POST "https://api.together.xyz/v1/audio/transcriptions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -F model="openai/whisper-large-v3" \
  -F file=@audio.mp3