Alibaba Cloud Model Studio:Voice cloning

# Requirements: dashscope >= 1.26.5, pyaudio
import os
import requests
import base64
import pathlib
import time
import pyaudio
from dashscope.audio.qwen_omni import MultiModality, OmniRealtimeCallback, OmniRealtimeConversation
import dashscope
# China (Beijing) region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"

# ======= Configuration =======
DEFAULT_TARGET_MODEL = "qwen3.8-omni-flash-realtime"  # Must be the same model for cloning and conversation
DEFAULT_PREFERRED_NAME = "guanyu"
DEFAULT_AUDIO_MIME_TYPE = "audio/mpeg"
VOICE_FILE_PATH = "voice.mp3"  # Path to the local audio file for voice cloning

def create_voice(file_path: str,
                 target_model: str = DEFAULT_TARGET_MODEL,
                 preferred_name: str = DEFAULT_PREFERRED_NAME,
                 audio_mime_type: str = DEFAULT_AUDIO_MIME_TYPE) -> str:
    """
    Create a custom voice and return the voice parameter.
    """
    # API keys differ between the Singapore and Beijing regions. Get an API key: https://www.alibabacloud.com/help/model-studio/get-api-key
    # If you haven't set an environment variable, replace the following line with: api_key = "sk-xxx"
    api_key = os.getenv("DASHSCOPE_API_KEY")

    file_path_obj = pathlib.Path(file_path)
    if not file_path_obj.exists():
        raise FileNotFoundError(f"Audio file not found: {file_path}")

    base64_str = base64.b64encode(file_path_obj.read_bytes()).decode()
    data_uri = f"data:{audio_mime_type};base64,{base64_str}"

    # The following is the Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization"
    payload = {
        "model": "qwen-voice-enrollment",
        "parameters": {"voice_clone_mode": "normal"},
        "input": {
            "action": "create",
            "target_model": target_model,
            "preferred_name": preferred_name,
            "audio": {"data": data_uri}
        }
    }
    headers = {
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json"
    }

    resp = requests.post(url, json=payload, headers=headers)
    if resp.status_code != 200:
        raise RuntimeError(f"Failed to create voice: {resp.status_code}, {resp.text}")

    try:
        return resp.json()["output"]["voice"]
    except (KeyError, ValueError) as e:
        raise RuntimeError(f"Failed to parse voice response: {e}")

class SimpleCallback(OmniRealtimeCallback):
    def __init__(self, pya):
        self.pya = pya
        self.out = None
    def on_open(self):
        self.out = self.pya.open(
            format=pyaudio.paInt16,
            channels=1,
            rate=24000,
            output=True
        )
    def on_event(self, response):
        if response['type'] == 'response.audio.delta':
            self.out.write(base64.b64decode(response['delta']))
        elif response['type'] == 'conversation.item.input_audio_transcription.completed':
            print(f"[User] {response['transcript']}")
        elif response['type'] == 'response.audio_transcript.done':
            print(f"[LLM] {response['transcript']}")

if __name__ == '__main__':
    # If you haven't set an environment variable, replace the following line with: dashscope.api_key = "sk-xxx"
    dashscope.api_key = os.getenv("DASHSCOPE_API_KEY")
    # The following is the Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    url = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime"

    # Step 1: Clone a voice
    voice = create_voice(VOICE_FILE_PATH)
    print(f"Voice cloning complete. Voice: {voice}")

    # Step 2: Start a real-time conversation with the cloned voice
    pya = pyaudio.PyAudio()
    callback = SimpleCallback(pya)
    conv = OmniRealtimeConversation(model=DEFAULT_TARGET_MODEL, callback=callback, url=url)
    conv.connect()
    conv.update_session(
        output_modalities=[MultiModality.AUDIO, MultiModality.TEXT],
        voice=voice  # Use the cloned voice
    )
    mic = pya.open(format=pyaudio.paInt16, channels=1, rate=16000, input=True)
    print("Conversation started. Speak into your microphone (Ctrl+C to exit)...")
    try:
        while True:
            audio_data = mic.read(3200, exception_on_overflow=False)
            conv.append_audio(base64.b64encode(audio_data).decode())
            time.sleep(0.01)
    except KeyboardInterrupt:
        conv.close()
        mic.close()
        callback.out.close()
        pya.terminate()
        print("\nConversation ended")

import com.alibaba.dashscope.audio.omni.*;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.google.gson.Gson;
import com.google.gson.JsonObject;

import javax.sound.sampled.*;
import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.nio.ByteBuffer;
import java.nio.file.*;
import java.nio.charset.StandardCharsets;
import java.util.Arrays;
import java.util.Base64;
import java.util.Queue;
import java.util.concurrent.ConcurrentLinkedQueue;
import java.util.concurrent.atomic.AtomicBoolean;

public class Main {
    // ===== Constants =====
    // Use the same model for voice cloning and real-time conversation
    private static final String TARGET_MODEL = "qwen3.8-omni-flash-realtime";
    private static final String PREFERRED_NAME = "guanyu";
    // Relative path to the local audio file for voice cloning
    private static final String AUDIO_FILE = "voice.mp3";
    private static final String AUDIO_MIME_TYPE = "audio/mpeg";

    // Generate a data URI
    public static String toDataUrl(String filePath) throws IOException {
        byte[] bytes = Files.readAllBytes(Paths.get(filePath));
        String encoded = Base64.getEncoder().encodeToString(bytes);
        return "data:" + AUDIO_MIME_TYPE + ";base64," + encoded;
    }

    // Call the API to create a voice
    public static String createVoice() throws Exception {
        // The API keys for the Singapore and Beijing regions are different. Get an API key: https://www.alibabacloud.com/help/model-studio/get-api-key
        // If you haven't configured the environment variable, replace the following line with: String apiKey = "sk-xxx"
        String apiKey = System.getenv("DASHSCOPE_API_KEY");

        String jsonPayload =
                "{"
                        + "\"model\": \"qwen-voice-enrollment\","
                        + "\"parameters\": {\"voice_clone_mode\": \"normal\"},"
                        + "\"input\": {"
                        +     "\"action\": \"create\","
                        +     "\"target_model\": \"" + TARGET_MODEL + "\","
                        +     "\"preferred_name\": \"" + PREFERRED_NAME + "\","
                        +     "\"audio\": {"
                        +         "\"data\": \"" + toDataUrl(AUDIO_FILE) + "\""
                        +     "}"
                        + "}"
                        + "}";

        // The following is the Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
        String url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization";
        HttpURLConnection con = (HttpURLConnection) new URL(url).openConnection();
        con.setRequestMethod("POST");
        con.setRequestProperty("Authorization", "Bearer " + apiKey);
        con.setRequestProperty("Content-Type", "application/json");
        con.setDoOutput(true);

        try (OutputStream os = con.getOutputStream()) {
            os.write(jsonPayload.getBytes(StandardCharsets.UTF_8));
        }

        int status = con.getResponseCode();
        try (BufferedReader br = new BufferedReader(
                new InputStreamReader(status >= 200 && status < 300 ? con.getInputStream() : con.getErrorStream(),
                        StandardCharsets.UTF_8))) {
            StringBuilder response = new StringBuilder();
            String line;
            while ((line = br.readLine()) != null) {
                response.append(line);
            }
            if (status == 200) {
                JsonObject jsonObj = new Gson().fromJson(response.toString(), JsonObject.class);
                return jsonObj.getAsJsonObject("output").get("voice").getAsString();
            }
            throw new IOException("Failed to create voice: " + status + " - " + response);
        }
    }

    // Simple audio player
    static class SimpleAudioPlayer {
        private final SourceDataLine line;
        private final Queue<byte[]> audioQueue = new ConcurrentLinkedQueue<>();
        private final Thread playerThread;
        private final AtomicBoolean shouldStop = new AtomicBoolean(false);

        public SimpleAudioPlayer() throws LineUnavailableException {
            AudioFormat format = new AudioFormat(24000, 16, 1, true, false);
            line = AudioSystem.getSourceDataLine(format);
            line.open(format);
            line.start();
            playerThread = new Thread(() -> {
                while (!shouldStop.get()) {
                    byte[] audio = audioQueue.poll();
                    if (audio != null) {
                        line.write(audio, 0, audio.length);
                    } else {
                        try { Thread.sleep(10); } catch (InterruptedException ignored) {}
                    }
                }
            }, "AudioPlayer");
            playerThread.start();
        }

        public void play(String base64Audio) {
            audioQueue.add(Base64.getDecoder().decode(base64Audio));
        }

        public void close() {
            shouldStop.set(true);
            try { playerThread.join(1000); } catch (InterruptedException ignored) {}
            line.drain();
            line.close();
        }
    }

    public static void main(String[] args) {
        try {
            // 1. Voice cloning: create a custom voice
            String voice = createVoice();
            System.out.println("Voice cloning complete. Voice: " + voice);

            // 2. Use the cloned voice in a real-time conversation
            SimpleAudioPlayer player = new SimpleAudioPlayer();
            AtomicBoolean shouldStop = new AtomicBoolean(false);

            OmniRealtimeParam param = OmniRealtimeParam.builder()
                    .model(TARGET_MODEL)
                    // The API keys for the Singapore and Beijing regions are different. Get an API key: https://www.alibabacloud.com/help/model-studio/get-api-key
                    // If you haven't configured the environment variable, replace the following line with: .apikey("sk-xxx")
                    .apikey(System.getenv("DASHSCOPE_API_KEY"))
                    // The following is the Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
                    .url("wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime")
                    .build();

            OmniRealtimeConversation conversation = new OmniRealtimeConversation(param, new OmniRealtimeCallback() {
                @Override public void onOpen() { System.out.println("Connection established"); }
                @Override public void onClose(int code, String reason) {
                    System.out.println("Connection closed (" + code + "): " + reason);
                    shouldStop.set(true);
                }
                @Override public void onEvent(JsonObject event) {
                    String type = event.get("type").getAsString();
                    if ("response.audio.delta".equals(type)) {
                        player.play(event.get("delta").getAsString());
                    } else if ("conversation.item.input_audio_transcription.completed".equals(type)) {
                        System.out.println("[User] " + event.get("transcript").getAsString());
                    } else if ("response.audio_transcript.done".equals(type)) {
                        System.out.println("[LLM] " + event.get("transcript").getAsString());
                    }
                }
            });

            conversation.connect();
            conversation.updateSession(OmniRealtimeConfig.builder()
                    .modalities(Arrays.asList(OmniRealtimeModality.AUDIO, OmniRealtimeModality.TEXT))
                    .voice(voice)  // Use the cloned custom voice
                    .enableTurnDetection(true)
                    .enableInputAudioTranscription(true)
                    .build()
            );

            System.out.println("Conversation started. Speak into the microphone (Ctrl+C to exit)...");
            AudioFormat format = new AudioFormat(16000, 16, 1, true, false);
            TargetDataLine mic = AudioSystem.getTargetDataLine(format);
            mic.open(format);
            mic.start();

            ByteBuffer buffer = ByteBuffer.allocate(3200);
            while (!shouldStop.get()) {
                int bytesRead = mic.read(buffer.array(), 0, buffer.capacity());
                if (bytesRead > 0) {
                    conversation.appendAudio(Base64.getEncoder().encodeToString(buffer.array()));
                }
                Thread.sleep(20);
            }

            conversation.close(1000, "Normal exit");
            player.close();
            mic.close();
            System.out.println("\nConversation ended");
        } catch (NoApiKeyException e) {
            System.err.println("API KEY not found. Set the DASHSCOPE_API_KEY environment variable.");
        } catch (Exception e) {
            e.printStackTrace();
        }
        System.exit(0);
    }
}

# Requirements: dashscope >= 1.23.9, soundfile, numpy
import os
import requests
import base64
import pathlib
import numpy as np
import soundfile as sf
import dashscope
# China (Beijing) region. Replace {WorkspaceId} with your Bailian workspace ID. URLs vary by region.
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"

# ======= Configuration =======
DEFAULT_TARGET_MODEL = "qwen3.5-omni-plus"  # Voice cloning and non-realtime calls must use the same model
DEFAULT_PREFERRED_NAME = "guanyu"
DEFAULT_AUDIO_MIME_TYPE = "audio/mpeg"
VOICE_FILE_PATH = "voice.mp3"  # Path to the local audio file for voice cloning

def create_voice(file_path: str,
                 target_model: str = DEFAULT_TARGET_MODEL,
                 preferred_name: str = DEFAULT_PREFERRED_NAME,
                 audio_mime_type: str = DEFAULT_AUDIO_MIME_TYPE) -> str:
    """
    Create a custom voice and return the voice parameter.
    """
    # API keys differ between Singapore and Beijing regions. Get an API key: https://www.alibabacloud.com/help/model-studio/get-api-key
    # If the environment variable is not configured, replace the following line with: api_key = "sk-xxx"
    api_key = os.getenv("DASHSCOPE_API_KEY")

    file_path_obj = pathlib.Path(file_path)
    if not file_path_obj.exists():
        raise FileNotFoundError(f"Audio file not found: {file_path}")

    base64_str = base64.b64encode(file_path_obj.read_bytes()).decode()
    data_uri = f"data:{audio_mime_type};base64,{base64_str}"

    # The following is the Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization"
    payload = {
        "model": "qwen-voice-enrollment",
        "input": {
            "action": "create",
            "target_model": target_model,
            "preferred_name": preferred_name,
            "audio": {"data": data_uri}
        }
    }
    headers = {
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json"
    }

    resp = requests.post(url, json=payload, headers=headers)
    if resp.status_code != 200:
        raise RuntimeError(f"Failed to create voice: {resp.status_code}, {resp.text}")

    try:
        return resp.json()["output"]["voice"]
    except (KeyError, ValueError) as e:
        raise RuntimeError(f"Failed to parse voice response: {e}")

if __name__ == '__main__':
    # The following is the Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

    # 1. Voice cloning: create a custom voice
    voice = create_voice(VOICE_FILE_PATH)
    print(f"Voice cloning complete. Voice: {voice}")

    # 2. Non-realtime conversation with the cloned voice
    messages = [{"role": "user", "content": [{"text": "Hello, please introduce yourself"}]}]

    response = dashscope.MultiModalConversation.call(
        # If the environment variable is not configured, replace with: api_key="sk-xxx"
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        model=DEFAULT_TARGET_MODEL,
        messages=messages,
        modalities=["text", "audio"],
        audio={"voice": voice, "format": "wav"},  # Use the cloned voice
        stream=True
    )

    print("Model response:")
    audio_base64_string = ""
    for r in response:
        try:
            content = r.output.choices[0].message.content
            for item in content:
                if isinstance(item, dict):
                    if "audio" in item:
                        audio_base64_string += item["audio"].get("data", "")
                    elif "text" in item:
                        print(item["text"], end="")
        except Exception:
            pass

    if audio_base64_string:
        wav_bytes = base64.b64decode(audio_base64_string)
        audio_np = np.frombuffer(wav_bytes, dtype=np.int16)
        sf.write("audio_cloned.wav", audio_np, samplerate=24000)
        print("\nAudio saved to: audio_cloned.wav")

import com.google.gson.Gson;
import com.google.gson.JsonObject;

import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.nio.ByteBuffer;
import java.nio.ByteOrder;
import java.nio.file.*;
import java.nio.charset.StandardCharsets;
import java.util.Base64;

public class Main {
    // ===== Constants =====
    // Voice cloning and non-realtime calls must use the same model
    private static final String TARGET_MODEL = "qwen3.5-omni-plus";
    private static final String PREFERRED_NAME = "guanyu";
    // Path to the local audio file for voice cloning
    private static final String AUDIO_FILE = "voice.mp3";
    private static final String AUDIO_MIME_TYPE = "audio/mpeg";

    // Write PCM data as a standard WAV file
    public static void writeWav(String path, byte[] pcmData, int sampleRate) throws IOException {
        int channels = 1, bitsPerSample = 16;
        int byteRate = sampleRate * channels * bitsPerSample / 8;
        int blockAlign = channels * bitsPerSample / 8;
        ByteBuffer header = ByteBuffer.allocate(44).order(ByteOrder.LITTLE_ENDIAN);
        header.put("RIFF".getBytes()); header.putInt(36 + pcmData.length);
        header.put("WAVE".getBytes()); header.put("fmt ".getBytes());
        header.putInt(16); header.putShort((short) 1); header.putShort((short) channels);
        header.putInt(sampleRate); header.putInt(byteRate);
        header.putShort((short) blockAlign); header.putShort((short) bitsPerSample);
        header.put("data".getBytes()); header.putInt(pcmData.length);
        try (FileOutputStream fos = new FileOutputStream(path)) {
            fos.write(header.array());
            fos.write(pcmData);
        }
    }

    // Generate a data URI from a file
    public static String toDataUrl(String filePath) throws IOException {
        byte[] bytes = Files.readAllBytes(Paths.get(filePath));
        String encoded = Base64.getEncoder().encodeToString(bytes);
        return "data:" + AUDIO_MIME_TYPE + ";base64," + encoded;
    }

    // Call the API to create a voice
    public static String createVoice() throws Exception {
        // API keys differ between Singapore and Beijing regions. Get an API key: https://www.alibabacloud.com/help/model-studio/get-api-key
        // If the environment variable is not configured, replace the following line with: String apiKey = "sk-xxx"
        String apiKey = System.getenv("DASHSCOPE_API_KEY");

        String jsonPayload =
                "{"
                        + "\"model\": \"qwen-voice-enrollment\","
                        + "\"input\": {"
                        +     "\"action\": \"create\","
                        +     "\"target_model\": \"" + TARGET_MODEL + "\","
                        +     "\"preferred_name\": \"" + PREFERRED_NAME + "\","
                        +     "\"audio\": {"
                        +         "\"data\": \"" + toDataUrl(AUDIO_FILE) + "\""
                        +     "}"
                        + "}"
                        + "}";

        // The following is the Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
        String url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization";
        HttpURLConnection con = (HttpURLConnection) new URL(url).openConnection();
        con.setRequestMethod("POST");
        con.setRequestProperty("Authorization", "Bearer " + apiKey);
        con.setRequestProperty("Content-Type", "application/json");
        con.setDoOutput(true);

        try (OutputStream os = con.getOutputStream()) {
            os.write(jsonPayload.getBytes(StandardCharsets.UTF_8));
        }

        int status = con.getResponseCode();
        try (BufferedReader br = new BufferedReader(
                new InputStreamReader(status >= 200 && status < 300 ? con.getInputStream() : con.getErrorStream(),
                        StandardCharsets.UTF_8))) {
            StringBuilder response = new StringBuilder();
            String line;
            while ((line = br.readLine()) != null) {
                response.append(line);
            }
            if (status == 200) {
                JsonObject jsonObj = new Gson().fromJson(response.toString(), JsonObject.class);
                return jsonObj.getAsJsonObject("output").get("voice").getAsString();
            }
            throw new IOException("Failed to create voice: " + status + " - " + response);
        }
    }

    public static void main(String[] args) {
        try {
            // API keys differ between Singapore and Beijing regions. Get an API key: https://www.alibabacloud.com/help/model-studio/get-api-key
            // If the environment variable is not configured, replace the following line with: String apiKey = "sk-xxx"
            String apiKey = System.getenv("DASHSCOPE_API_KEY");

            // 1. Voice cloning: create a custom voice
            String voice = createVoice();
            System.out.println("Voice cloning complete. Voice: " + voice);

            // 2. Non-realtime conversation with the cloned voice (OpenAI-compatible API)
            String requestBody = "{"
                    + "\"model\": \"" + TARGET_MODEL + "\","
                    + "\"messages\": [{\"role\": \"user\", \"content\": \"Hello, please introduce yourself\"}],"
                    + "\"modalities\": [\"text\", \"audio\"],"
                    + "\"audio\": {\"voice\": \"" + voice + "\", \"format\": \"wav\"},"
                    + "\"stream\": true,"
                    + "\"stream_options\": {\"include_usage\": true}"
                    + "}";

            // The following is the Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
            String url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions";
            HttpURLConnection con = (HttpURLConnection) new URL(url).openConnection();
            con.setRequestMethod("POST");
            con.setRequestProperty("Authorization", "Bearer " + apiKey);
            con.setRequestProperty("Content-Type", "application/json");
            con.setDoOutput(true);

            try (OutputStream os = con.getOutputStream()) {
                os.write(requestBody.getBytes(StandardCharsets.UTF_8));
            }

            // 3. Parse streaming SSE response
            StringBuilder audioBase64 = new StringBuilder();
            System.out.println("Model response:");

            try (BufferedReader br = new BufferedReader(
                    new InputStreamReader(con.getInputStream(), StandardCharsets.UTF_8))) {
                String line;
                while ((line = br.readLine()) != null) {
                    if (!line.startsWith("data: ") || line.equals("data: [DONE]")) continue;
                    String json = line.substring(6);
                    JsonObject chunk = new Gson().fromJson(json, JsonObject.class);
                    if (!chunk.has("choices") || chunk.getAsJsonArray("choices").size() == 0) continue;

                    JsonObject delta = chunk.getAsJsonArray("choices").get(0)
                            .getAsJsonObject().getAsJsonObject("delta");
                    if (delta.has("content") && !delta.get("content").isJsonNull()) {
                        System.out.print(delta.get("content").getAsString());
                    }
                    if (delta.has("audio") && !delta.get("audio").isJsonNull()) {
                        JsonObject audio = delta.getAsJsonObject("audio");
                        if (audio.has("data")) {
                            audioBase64.append(audio.get("data").getAsString());
                        }
                    }
                }
            }

            // 4. Save audio file (API returns raw PCM data, WAV header required)
            if (audioBase64.length() > 0) {
                byte[] pcmBytes = Base64.getDecoder().decode(audioBase64.toString());
                writeWav("audio_cloned.wav", pcmBytes, 24000);
                System.out.println("\nAudio saved to: audio_cloned.wav");
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}