aliyun-qwen-tts-realtime

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Category: provider

分类: provider

Model Studio Qwen TTS Realtime

模型工作室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

```
qwen3-tts-vd-realtime-2026-01-15
```
```
qwen3-tts-vc-realtime-2026-01-15
```

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

```
qwen3-tts-vd-realtime-2026-01-15
```
```
qwen3-tts-vc-realtime-2026-01-15
```

Prerequisites

前置要求

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

，或者将

dashscope_api_key

添加到

~/.alibabacloud/credentials

文件中。

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，选填)
```
sample_rate
```
(整数，选填)

Response

返回参数

```
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

操作指引

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.

实时模式下请使用websocket或流式接口端点。
保持每段发音简短以获得更低延迟。
对于指令类模型，请保持指令明确简洁。
部分SDK/运行时组合可能会拒绝通过
```
MultiModalConversation
```
发起的实时模型调用；请使用下方的探测脚本来验证兼容性。

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/aliyun-qwen-tts-realtime/scripts/realtime_tts_demo.py \
  --text "This is a realtime speech demo." \
  --fallback \
  --output output/ai-audio-tts-realtime/audio/fallback-demo.wav

Strict mode (for CI / gating):

bash

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

使用探测脚本来验证当前SDK/运行时的实时兼容性，必要时可回退到非实时模型以获得即时输出：

bash

.venv/bin/python skills/ai/audio/aliyun-qwen-tts-realtime/scripts/realtime_tts_demo.py \
  --text "This is a realtime speech demo." \
  --fallback \
  --output output/ai-audio-tts-realtime/audio/fallback-demo.wav

严格模式（用于CI/门禁校验）：

bash

.venv/bin/python skills/ai/audio/aliyun-qwen-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
```
环境变量覆盖基础目录。

Validation

校验

bash

mkdir -p output/aliyun-qwen-tts-realtime
for f in skills/ai/audio/aliyun-qwen-tts-realtime/scripts/*.py; do
  python3 -m py_compile "$f"
done
echo "py_compile_ok" > output/aliyun-qwen-tts-realtime/validate.txt

Pass criteria: command exits 0 and

output/aliyun-qwen-tts-realtime/validate.txt

is generated.

bash

mkdir -p output/aliyun-qwen-tts-realtime
for f in skills/ai/audio/aliyun-qwen-tts-realtime/scripts/*.py; do
  python3 -m py_compile "$f"
done
echo "py_compile_ok" > output/aliyun-qwen-tts-realtime/validate.txt

通过标准：命令退出码为0，且成功生成

output/aliyun-qwen-tts-realtime/validate.txt

文件。

Output And Evidence

输出与凭证

Save artifacts, command outputs, and API response summaries under
```
output/aliyun-qwen-tts-realtime/
```
.
Include key parameters (region/resource id/time range) in evidence files for reproducibility.

将产物、命令输出和API响应摘要保存在
```
output/aliyun-qwen-tts-realtime/
```
目录下。
请在凭证文件中包含关键参数（区域/资源ID/时间范围）以保证可复现性。

Workflow

工作流

Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
Run one minimal read-only query first to verify connectivity and permissions.
Execute the target operation with explicit parameters and bounded scope.
Verify results and save output/evidence files.

确认用户意图、区域、标识符，以及操作是只读还是可修改类型。
先运行一个最小化的只读查询来验证连通性和权限。
使用明确的参数和有限的范围执行目标操作。
验证结果并保存输出/凭证文件。

References

参考文档

```
references/sources.md
```

```
references/sources.md
```