alicloud-ai-audio-tts-realtime

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Category: provider

分类：服务商

Model Studio Qwen TTS Realtime

Use realtime TTS models for low-latency streaming speech output.

使用实时TTS模型实现低延迟流式语音输出。

Critical model names

关键模型名称

Use one of these exact model strings:

```
qwen3-tts-flash-realtime
```
```
qwen3-tts-instruct-flash-realtime
```

qwen3-tts-instruct-flash-realtime-2026-01-22

请使用以下精确的模型字符串之一：

```
qwen3-tts-flash-realtime
```
```
qwen3-tts-instruct-flash-realtime
```

qwen3-tts-instruct-flash-realtime-2026-01-22

Prerequisites

前提条件

Install SDK in a virtual environment:

bash

python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope

Set

DASHSCOPE_API_KEY

in your environment, or add

dashscope_api_key

~/.alibabacloud/credentials

在虚拟环境中安装SDK：

bash

python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope

在环境变量中设置

DASHSCOPE_API_KEY

，或在

~/.alibabacloud/credentials

中添加

dashscope_api_key

。

Normalized interface (tts.realtime)

标准化接口（tts.realtime）

Request

请求参数

```
text
```
(string, required)
```
voice
```
(string, required)
```
instruction
```
(string, optional)
```
sample_rate
```
(int, optional)

```
text
```
（字符串，必填）
```
voice
```
（字符串，必填）
```
instruction
```
（字符串，可选）
```
sample_rate
```
（整数，可选）

Response

响应结果

```
audio_base64_pcm_chunks
```
(array<string>)
```
sample_rate
```
(int)
```
finish_reason
```
(string)

```
audio_base64_pcm_chunks
```
（字符串数组）
```
sample_rate
```
（整数）
```
finish_reason
```
（字符串）

Operational guidance

操作指南

Use websocket or streaming endpoint for realtime mode.
Keep each utterance short for lower latency.
For instruction models, keep instruction explicit and concise.
Some SDK/runtime combinations may reject realtime model calls over
```
MultiModalConversation
```
; use the probe script below to verify compatibility.

使用websocket或流式端点进行实时模式调用。
保持每段语音内容简短以降低延迟。
对于指令型模型，确保指令明确简洁。
部分SDK/运行时组合可能会拒绝通过
```
MultiModalConversation
```
调用实时模型；使用下方的探测脚本验证兼容性。

Local demo script

本地演示脚本

Use the probe script to verify realtime compatibility in your current SDK/runtime, and optionally fallback to a non-realtime model for immediate output:

bash

.venv/bin/python skills/ai/audio/alicloud-ai-audio-tts-realtime/scripts/realtime_tts_demo.py \
  --text "这是一个 realtime 语音演示。" \
  --fallback \
  --output output/ai-audio-tts-realtime/audio/fallback-demo.wav

Strict mode (for CI / gating):

bash

.venv/bin/python skills/ai/audio/alicloud-ai-audio-tts-realtime/scripts/realtime_tts_demo.py \
  --text "realtime health check" \
  --strict

使用探测脚本验证当前SDK/运行时的实时兼容性，也可选择回退到非实时模型以立即输出：

bash

.venv/bin/python skills/ai/audio/alicloud-ai-audio-tts-realtime/scripts/realtime_tts_demo.py \
  --text "这是一个 realtime 语音演示。" \
  --fallback \
  --output output/ai-audio-tts-realtime/audio/fallback-demo.wav

严格模式（适用于CI / 门禁检测）：

bash

.venv/bin/python skills/ai/audio/alicloud-ai-audio-tts-realtime/scripts/realtime_tts_demo.py \
  --text "realtime health check" \
  --strict

Output location

输出位置

Default output:
```
output/ai-audio-tts-realtime/audio/
```
Override base dir with
```
OUTPUT_DIR
```
.

默认输出路径：
```
output/ai-audio-tts-realtime/audio/
```
可通过
```
OUTPUT_DIR
```
覆盖基础目录。

References

参考资料

```
references/sources.md
```

```
references/sources.md
```