> ## Documentation Index > Fetch the complete documentation index at: https://docs.modelstudio.console.alibabacloud.com/llms.txt > Use this file to discover all available pages before exploring further. # Qwen-TTS non-real-time speech synthesis API reference > Request parameters and response fields for the non-realtime speech synthesis (Qwen-TTS) API.
## Request body > In DashScope Python SDK 2.0, non-realtime speech synthesis is called through the `client.audio.tts.http` resource. ```python # Install the latest version of the DashScope SDK import os import dashscope # The following is the configuration for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. The region value varies by region. client = dashscope.Client( # The API keys for Singapore and Beijing regions are different. Get your API key: https://www.alibabacloud.com/help/model-studio/get-api-key # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx" api_key=os.getenv("DASHSCOPE_API_KEY"), workspace="{WorkspaceId}", region="ap-southeast-1", ) text = "Let me recommend a T-shirt to everyone. This one is really super nice. The color is very elegant, and it's also a perfect item to match. Everyone can buy it without hesitation. It's truly beautiful and very forgiving on the figure. No matter what body type you have, it will look great. I recommend everyone to place an order." result = client.audio.tts.http.synthesize( text, model="qwen3-tts-flash", voice="Cherry" ) print(result.audio_url, result.audio_id, result.expires_at) ``` ```java expandable // Install the latest version of the DashScope SDK import com.alibaba.dashscope.aigc.multimodalconversation.AudioParameters; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult; import com.alibaba.dashscope.exception.ApiException; import com.alibaba.dashscope.exception.NoApiKeyException; import com.alibaba.dashscope.exception.UploadFileException; import com.alibaba.dashscope.utils.JsonUtils; import com.alibaba.dashscope.utils.Constants; public class Main { private static final String MODEL = "qwen3-tts-flash"; public static void call() throws ApiException, NoApiKeyException, UploadFileException { MultiModalConversation conv = new MultiModalConversation(); MultiModalConversationParam param = MultiModalConversationParam.builder() .model(MODEL) // The API keys for Singapore and Beijing regions are different. Get your API Key: https://www.alibabacloud.com/help/model-studio/get-api-key // If the environment variable is not configured, replace the following line with your Model Studio API key: apiKey("sk-xxx") .apiKey(System.getenv("DASHSCOPE_API_KEY")) .text("Today is a wonderful day to build something people love!") .voice(AudioParameters.Voice.CHERRY) .parameter("language_type", "English") .build(); MultiModalConversationResult result = conv.call(param); System.out.println(JsonUtils.toJson(result)); } public static void main(String[] args) { // Singapore region Constants.baseHttpApiUrl = "https://dashscope-intl.aliyuncs.com/api/v1"; try { call(); } catch (ApiException | NoApiKeyException | UploadFileException e) { System.out.println(e.getMessage()); } System.exit(0); } } ``` ```bash # ======= IMPORTANT NOTE ======= # Singapore region # The API keys for Singapore and Beijing regions are different. Get your API Key: https://www.alibabacloud.com/help/model-studio/get-api-key # If the environment variable is not configured, replace $DASHSCOPE_API_KEY with your Model Studio API key: sk-xxx. # === DELETE THIS COMMENT WHEN EXECUTING === curl -X POST 'https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \ -H "Authorization: Bearer $DASHSCOPE_API_KEY" \ -H 'Content-Type: application/json' \ -d '{ "model": "qwen3-tts-flash", "input": { "text": "Let me recommend a T-shirt to everyone. This one is really super nice. The color is very elegant, and it's also a perfect item to match. Everyone can buy it without hesitation. It's truly beautiful and very forgiving on the figure. No matter what body type you have, it will look great. I recommend everyone to place an order.", "voice": "Cherry", "language_type": "English" } }' ``` > In DashScope Python SDK 2.0, non-realtime speech synthesis is called through the `client.audio.tts.http` resource. ```python # DashScope SDK version 2.0.1 or later required import os import dashscope # The following is the configuration for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. The region value varies by region. client = dashscope.Client( # The API keys for Singapore and Beijing regions are different. Get your API key: https://www.alibabacloud.com/help/model-studio/get-api-key # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx" api_key=os.getenv("DASHSCOPE_API_KEY"), workspace="{WorkspaceId}", region="ap-southeast-1", ) text = "Let me recommend a T-shirt to everyone. This one is really super nice. The color is very elegant, and it's also a perfect item to match. Everyone can buy it without hesitation. It's truly beautiful and very forgiving on the figure. No matter what body type you have, it will look great. I recommend everyone to place an order." for chunk in client.audio.tts.http.stream( text, model="qwen3-tts-flash", voice="Cherry", ): # chunk.audio contains the decoded audio bytes (bytes); when chunk.is_final is True, the chunk carries the URL of the full audio print(chunk) ``` ```java expandable // DashScope SDK version 2.19.0 or later required import com.alibaba.dashscope.aigc.multimodalconversation.AudioParameters; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult; import com.alibaba.dashscope.exception.ApiException; import com.alibaba.dashscope.exception.NoApiKeyException; import com.alibaba.dashscope.exception.UploadFileException; import com.alibaba.dashscope.utils.JsonUtils; import com.alibaba.dashscope.utils.Constants; import io.reactivex.Flowable; public class Main { private static final String MODEL = "qwen3-tts-flash"; public static void streamCall() throws ApiException, NoApiKeyException, UploadFileException { MultiModalConversation conv = new MultiModalConversation(); MultiModalConversationParam param = MultiModalConversationParam.builder() .model(MODEL) // The API keys for Singapore and Beijing regions are different. Get your API Key: https://www.alibabacloud.com/help/model-studio/get-api-key // If the environment variable is not configured, replace the following line with your Model Studio API key: apiKey("sk-xxx") .apiKey(System.getenv("DASHSCOPE_API_KEY")) .text("Today is a wonderful day to build something people love!") .voice(AudioParameters.Voice.CHERRY) .parameter("language_type", "English") .build(); Flowable result = conv.streamCall(param); result.blockingForEach(r -> {System.out.println(JsonUtils.toJson(r)); }); } public static void main(String[] args) { // Singapore region Constants.baseHttpApiUrl = "https://dashscope-intl.aliyuncs.com/api/v1"; try { streamCall(); } catch (ApiException | NoApiKeyException | UploadFileException e) { System.out.println(e.getMessage()); } System.exit(0); } } ``` ```bash # ======= IMPORTANT NOTE ======= # Singapore region # The API keys for Singapore and Beijing regions are different. Get your API Key: https://www.alibabacloud.com/help/model-studio/get-api-key # If the environment variable is not configured, replace $DASHSCOPE_API_KEY with your Model Studio API key: sk-xxx. # === DELETE THIS COMMENT WHEN EXECUTING === curl -X POST 'https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \ -H "Authorization: Bearer $DASHSCOPE_API_KEY" \ -H 'Content-Type: application/json' \ -H 'X-DashScope-SSE: enable' \ -d '{ "model": "qwen3-tts-flash", "input": { "text": "Let me recommend a T-shirt to you. This one is truly stunning. Its color highlights your elegance and makes it an ideal match for any outfit. You can buy it without hesitation - it looks great on everyone. It flatters all body types. Whether you're tall, short, slim, or curvy, this T-shirt suits you perfectly. We highly recommend ordering it.", "voice": "Cherry", "language_type": "English" } }' ``` For real-time playback of Base64-encoded audio, see [Streaming playback](/en/model-studio/qwen-tts-api#qwen-tts-streaming-playback).
model`string`(required) The model name. For details, see [Supported models](/en/model-studio/non-realtime-tts-user-guide#d2ad2470a394c).
input`object`(required) Input parameters. text `string` (required) The text to synthesize. Supports multilingual mixed input. The maximum input length is 600 characters. voice `string` (required) The voice to use. See [Supported system voices](/en/model-studio/non-realtime-tts-user-guide#bac280ddf5a1u). language\_type `string` (optional) The language of the synthesized audio. Defaults to `Auto`. - `Auto`: Use when the input contains multiple languages or the language cannot be determined. The model automatically matches pronunciation for each language segment, though accuracy is not guaranteed. - Specific language: Use for single-language text. Specifying the language significantly improves synthesis quality and typically produces better results than `Auto`. Valid values: - `Chinese` - `English` - `German` - `Italian` - `Portuguese` - `Spanish` - `Japanese` - `Korean` - `French` - `Russian`
## Response object (streaming and non-streaming formats are identical) ```json Qwen3-TTS-Flash { "status_code": 200, "request_id": "5c63c65c-cad8-4bf4-959d-xxxxxxxxxxxx", "code": "", "message": "", "output": { "text": null, "finish_reason": "stop", "choices": null, "audio": { "data": "", "url": "http://dashscope-result-bj.oss-cn-beijing.aliyuncs.com/1d/ab/20251218/d2033070/39b6d8f2-c0db-4daa-9073-5d27bfb66b78.wav?Expires=1766113409&OSSAccessKeyId=YOUR_ACCESS_KEY_ID&Signature=YOUR_SIGNATURE", "id": "audio_5c63c65c-cad8-4bf4-959d-xxxxxxxxxxxx", "expires_at": 1766113409 } }, "usage": { "input_tokens": 0, "output_tokens": 0, "characters": 195 } } ```
status\_code `integer` The HTTP status code as defined in [RFC 9110](https://www.rfc-editor.org/rfc/rfc9110.html#name-status-codes). Common values:
• `200`: Request succeeded.
• `400`: Invalid request parameters.
• `401`: Unauthorized.
• `404`: Resource not found.
• `500`: Internal server error.
request\_id `string` A unique identifier for this request. Use it for troubleshooting.
code `string` The error code returned on failure. See [Error codes](/en/model-studio/error-code).
message `string` The error message returned on failure. See [Error codes](/en/model-studio/error-code).
output`object` The model output. text`string` Always null. Ignore this field. choices`string` Always null. Ignore this field. finish\_reason`string` The generation status: - `null` — Generation is in progress. - `stop` — Generation finished normally, or a stop condition was met. audio `object` The audio output from the model. url `string` The URL of the complete audio file, valid for 24 hours. In non-streaming mode, returned directly in the response. In streaming mode, only returned in the last chunk of the SSE stream (intermediate chunks do not contain this field). data `string` Base64-encoded audio data. In non-streaming mode, this field is always an empty string (use `url` to get the complete audio file). In streaming mode, intermediate chunks contain Base64-encoded audio segments, while the last chunk returns an empty string (use `url` to get the complete audio). id `string` A unique identifier for the audio. expires\_at `integer` The URL expiration time as a Unix timestamp.
usage `object` Character usage for this request. output\_tokens `integer` The number of tokens consumed by the output audio. For the Qwen3-TTS-Flash model, this field is always 0. input\_tokens `integer` The number of tokens consumed by the input text. For the Qwen3-TTS-Flash model, this field is always 0. characters `integer` The number of characters in the input text. Returned only by the Qwen3-TTS-Flash model.
request\_id `string` A unique identifier for this request. Use it for troubleshooting.
## Audio download and playback Before running the examples, [obtain and configure an API key](/en/model-studio/get-api-key) and [install the DashScope SDK](/en/model-studio/install-sdk). The Python playback example also requires PyAudio and NumPy. See the code comments for PyAudio installation instructions, and install NumPy with `pip install numpy`. ### Download audio (Java) You must import the Gson dependency. Add it using Maven or Gradle: Add the following to `pom.xml`: ```xml com.google.code.gson gson 2.13.1 ``` Add the following to `build.gradle`: ```gradle // https://mvnrepository.com/artifact/com.google.code.gson/gson implementation("com.google.code.gson:gson:2.13.1") ``` ```java expandable import com.alibaba.dashscope.aigc.multimodalconversation.AudioParameters; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult; import com.alibaba.dashscope.exception.ApiException; import com.alibaba.dashscope.exception.NoApiKeyException; import com.alibaba.dashscope.exception.UploadFileException; import com.alibaba.dashscope.utils.Constants; import java.io.FileOutputStream; import java.io.InputStream; import java.net.URL; public class Main { private static final String MODEL = "qwen3-tts-flash"; public static void call() throws ApiException, NoApiKeyException, UploadFileException { MultiModalConversation conv = new MultiModalConversation(); MultiModalConversationParam param = MultiModalConversationParam.builder() // 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 have not configured the environment variable, replace the following line with your Model Studio API Key: .apiKey("sk-xxx") .apiKey(System.getenv("DASHSCOPE_API_KEY")) .model(MODEL) .text("Today is a wonderful day to build something people love!") .voice(AudioParameters.Voice.CHERRY) .languageType("English") // We recommend matching this with the language of the text for correct pronunciation and natural intonation. .build(); MultiModalConversationResult result = conv.call(param); String audioUrl = result.getOutput().getAudio().getUrl(); System.out.print(audioUrl); // Download the audio file to local storage try (InputStream in = new URL(audioUrl).openStream(); FileOutputStream out = new FileOutputStream("downloaded_audio.wav")) { byte[] buffer = new byte[1024]; int bytesRead; while ((bytesRead = in.read(buffer)) != -1) { out.write(buffer, 0, bytesRead); } System.out.println("\nAudio file downloaded to: downloaded_audio.wav"); } catch (Exception e) { System.out.println("\nFailed to download audio file: " + e.getMessage()); } } public static void main(String[] args) { // The following is the configuration for the Singapore region. Constants.baseHttpApiUrl = "https://dashscope-intl.aliyuncs.com/api/v1"; try { call(); } catch (ApiException | NoApiKeyException | UploadFileException e) { System.out.println(e.getMessage()); } System.exit(0); } } ``` ### Streaming playback ```python expandable # coding=utf-8 # # Installation instructions for pyaudio: # APPLE Mac OS X # brew install portaudio # pip install pyaudio # Debian/Ubuntu # sudo apt-get install python-pyaudio python3-pyaudio # or # pip install pyaudio # CentOS # sudo yum install -y portaudio portaudio-devel && pip install pyaudio # Microsoft Windows # python -m pip install pyaudio import os import dashscope import pyaudio import time # The following is the configuration for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. The region value varies by region. client = dashscope.Client( # 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 the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx" api_key=os.getenv("DASHSCOPE_API_KEY"), workspace="{WorkspaceId}", region="ap-southeast-1", ) p = pyaudio.PyAudio() # Create an audio stream stream = p.open(format=pyaudio.paInt16, channels=1, rate=24000, output=True) text = "Today is a wonderful day to build something people love!" for chunk in client.audio.tts.http.stream( text, model="qwen3-tts-flash", voice="Cherry", language_type="English", # We recommend matching this with the language of the text for correct pronunciation and natural intonation. ): if chunk.audio: # Play the audio data directly (chunk.audio contains the decoded audio bytes) stream.write(chunk.audio) if chunk.is_final: print(f"finish at: {chunk.expires_at}") time.sleep(0.8) # Clean up resources stream.stop_stream() stream.close() p.terminate() ``` You must import the Gson dependency. Add it using Maven or Gradle: Add the following to `pom.xml`: ```xml com.google.code.gson gson 2.13.1 ``` Add the following to `build.gradle`: ```gradle // https://mvnrepository.com/artifact/com.google.code.gson/gson implementation("com.google.code.gson:gson:2.13.1") ``` ```java expandable // Please install the latest version of the DashScope SDK import com.alibaba.dashscope.aigc.multimodalconversation.AudioParameters; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam; import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult; import com.alibaba.dashscope.exception.ApiException; import com.alibaba.dashscope.exception.NoApiKeyException; import com.alibaba.dashscope.exception.UploadFileException; import com.alibaba.dashscope.utils.Constants; import io.reactivex.Flowable; import javax.sound.sampled.*; import java.util.Base64; public class Main { private static final String MODEL = "qwen3-tts-flash"; public static void streamCall() throws ApiException, NoApiKeyException, UploadFileException { MultiModalConversation conv = new MultiModalConversation(); MultiModalConversationParam param = MultiModalConversationParam.builder() // 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 have not configured the environment variable, replace the following line with your Model Studio API Key: .apiKey("sk-xxx") .apiKey(System.getenv("DASHSCOPE_API_KEY")) .model(MODEL) .text("Today is a wonderful day to build something people love!") .voice(AudioParameters.Voice.CHERRY) .languageType("English") // We recommend matching this with the language of the text for correct pronunciation and natural intonation. .build(); Flowable result = conv.streamCall(param); result.blockingForEach(r -> { try { // 1. Get the Base64-encoded audio data String base64Data = r.getOutput().getAudio().getData(); byte[] audioBytes = Base64.getDecoder().decode(base64Data); // 2. Configure the audio format (adjust according to the audio format returned by the API) AudioFormat format = new AudioFormat( AudioFormat.Encoding.PCM_SIGNED, 24000, // Sample rate (must match the format returned by the API) 16, // Bit depth 1, // Number of channels 2, // Frame size (in bytes) 24000, // Frame rate (must match the sample rate) false // Big-endian ); // 3. Play audio data in real time DataLine.Info info = new DataLine.Info(SourceDataLine.class, format); try (SourceDataLine line = (SourceDataLine) AudioSystem.getLine(info)) { if (line != null) { line.open(format); line.start(); line.write(audioBytes, 0, audioBytes.length); line.drain(); } } } catch (LineUnavailableException e) { e.printStackTrace(); } }); } public static void main(String[] args) { // The following is the configuration for the Singapore region. Constants.baseHttpApiUrl = "https://dashscope-intl.aliyuncs.com/api/v1"; try { streamCall(); } catch (ApiException | NoApiKeyException | UploadFileException e) { System.out.println(e.getMessage()); } System.exit(0); } } ```