aliyun-qwen-tts

Name: aliyun-qwen-tts
Author: cinience

63installs34forks

How to install aliyun-qwen-tts?

cinience/alicloud-skills/aliyun-qwen-tts

$npx -y skills add cinience/alicloud-skills --skill aliyun-qwen-tts

Installs into the current project.

Summary

Use when generating human-like speech audio with Model Studio DashScope Qwen TTS models (qwen3-tts-flash, qwen3-tts-instruct-flash). Use when converting text to speech, producing voice lines for short drama/news videos, or documenting TTS request/response fields for DashScope.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen TTS
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-qwen-tts
9	python -m py_compile skills/ai/audio/aliyun-qwen-tts/scripts/generate_tts.py && echo "py_compile_ok" > output/aliyun-qwen-tts/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-qwen-tts/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save generated audio links, sample audio files, and request payloads to `output/aliyun-qwen-tts/`.
17	- Keep one validation log per execution.
18
19	## Critical model names
20
21	Use one of the recommended models:
22	- `qwen3-tts-flash`
23	- `qwen3-tts-instruct-flash`
24	- `qwen3-tts-instruct-flash-2026-01-26`
25
26	## Prerequisites
27
28	- Install SDK (recommended in a venv to avoid PEP 668 limits):
29
30	```bash
31	python3 -m venv .venv
32	. .venv/bin/activate
33	python -m pip install dashscope
34	```
35	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials` (env takes precedence).
36
37	## Normalized interface (tts.generate)
38
39	### Request
40	- `text` (string, required)
41	- `voice` (string, required)
42	- `language_type` (string, optional; default `Auto`)
43	- `instruction` (string, optional; recommended for instruct models)
44	- `stream` (bool, optional; default false)
45
46	### Response
47	- `audio_url` (string, when stream=false)
48	- `audio_base64_pcm` (string, when stream=true)
49	- `sample_rate` (int, 24000)
50	- `format` (string, wav or pcm depending on mode)
51
52	## Quick start (Python + DashScope SDK)
53
54	```python
55	import os
56	import dashscope
57
58	# Prefer env var for auth: export DASHSCOPE_API_KEY=...
59	# Or use ~/.alibabacloud/credentials with dashscope_api_key under [default].
60	# Beijing region; for Singapore use: https://dashscope-intl.aliyuncs.com/api/v1
61	dashscope.base_http_api_url = "https://dashscope.aliyuncs.com/api/v1"
62
63	text = "Hello, this is a short voice line."
64	response = dashscope.MultiModalConversation.call(
65	model="qwen3-tts-instruct-flash",
66	api_key=os.getenv("DASHSCOPE_API_KEY"),
67	text=text,
68	voice="Cherry",
69	language_type="English",
70	instruction="Warm and calm tone, slightly slower pace.",
71	stream=False,
72	)
73
74	audio_url = response.output.audio.url
75	print(audio_url)
76	```
77
78	## Streaming notes
79
80	- `stream=True` returns Base64-encoded PCM chunks at 24kHz.
81	- Decode chunks and play or concatenate to a pcm buffer.
82	- The response contains `finish_reason == "stop"` when the stream ends.
83
84	## Operational guidance
85
86	- Keep requests concise; split long text into multiple calls if you hit size or timeout errors.
87	- Use `language_type` consistent with the text to improve pronunciation.
88	- Use `instruction` only when you need explicit style/tone control.
89	- Cache by `(text, voice, language_type)` to avoid repeat costs.
90
91	## Output location
92
93	- Default output: `output/aliyun-qwen-tts/audio/`
94	- Override base dir with `OUTPUT_DIR`.
95
96	## Workflow
97
98	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
99	2) Run one minimal read-only query first to verify connectivity and permissions.
100	3) Execute the target operation with explicit parameters and bounded scope.
101	4) Verify results and save output/evidence files.
102
103	## References
104
105	- `references/api_reference.md` for parameter mapping and streaming example.
106	- Realtime mode is provided by `skills/ai/audio/aliyun-qwen-tts-realtime/`.
107	- Voice cloning/design are provided by `skills/ai/audio/aliyun-qwen-tts-voice-clone/` and `skills/ai/audio/aliyun-qwen-tts-voice-design/`.
108
109	- Source list: `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-qwen-tts

63installs34forks

View on GitHub

How to install aliyun-qwen-tts?

cinience/alicloud-skills/aliyun-qwen-tts

$npx -y skills add cinience/alicloud-skills --skill aliyun-qwen-tts

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen TTS
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-qwen-tts
9	python -m py_compile skills/ai/audio/aliyun-qwen-tts/scripts/generate_tts.py && echo "py_compile_ok" > output/aliyun-qwen-tts/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-qwen-tts/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save generated audio links, sample audio files, and request payloads to `output/aliyun-qwen-tts/`.
17	- Keep one validation log per execution.
18
19	## Critical model names
20
21	Use one of the recommended models:
22	- `qwen3-tts-flash`
23	- `qwen3-tts-instruct-flash`
24	- `qwen3-tts-instruct-flash-2026-01-26`
25
26	## Prerequisites
27
28	- Install SDK (recommended in a venv to avoid PEP 668 limits):
29
30	```bash
31	python3 -m venv .venv
32	. .venv/bin/activate
33	python -m pip install dashscope
34	```
35	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials` (env takes precedence).
36
37	## Normalized interface (tts.generate)
38
39	### Request
40	- `text` (string, required)
41	- `voice` (string, required)
42	- `language_type` (string, optional; default `Auto`)
43	- `instruction` (string, optional; recommended for instruct models)
44	- `stream` (bool, optional; default false)
45
46	### Response
47	- `audio_url` (string, when stream=false)
48	- `audio_base64_pcm` (string, when stream=true)
49	- `sample_rate` (int, 24000)
50	- `format` (string, wav or pcm depending on mode)
51
52	## Quick start (Python + DashScope SDK)
53
54	```python
55	import os
56	import dashscope
57
58	# Prefer env var for auth: export DASHSCOPE_API_KEY=...
59	# Or use ~/.alibabacloud/credentials with dashscope_api_key under [default].
60	# Beijing region; for Singapore use: https://dashscope-intl.aliyuncs.com/api/v1
61	dashscope.base_http_api_url = "https://dashscope.aliyuncs.com/api/v1"
62
63	text = "Hello, this is a short voice line."
64	response = dashscope.MultiModalConversation.call(
65	model="qwen3-tts-instruct-flash",
66	api_key=os.getenv("DASHSCOPE_API_KEY"),
67	text=text,
68	voice="Cherry",
69	language_type="English",
70	instruction="Warm and calm tone, slightly slower pace.",
71	stream=False,
72	)
73
74	audio_url = response.output.audio.url
75	print(audio_url)
76	```
77
78	## Streaming notes
79
80	- `stream=True` returns Base64-encoded PCM chunks at 24kHz.
81	- Decode chunks and play or concatenate to a pcm buffer.
82	- The response contains `finish_reason == "stop"` when the stream ends.
83
84	## Operational guidance
85
86	- Keep requests concise; split long text into multiple calls if you hit size or timeout errors.
87	- Use `language_type` consistent with the text to improve pronunciation.
88	- Use `instruction` only when you need explicit style/tone control.
89	- Cache by `(text, voice, language_type)` to avoid repeat costs.
90
91	## Output location
92
93	- Default output: `output/aliyun-qwen-tts/audio/`
94	- Override base dir with `OUTPUT_DIR`.
95
96	## Workflow
97
98	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
99	2) Run one minimal read-only query first to verify connectivity and permissions.
100	3) Execute the target operation with explicit parameters and bounded scope.
101	4) Verify results and save output/evidence files.
102
103	## References
104
105	- `references/api_reference.md` for parameter mapping and streaming example.
106	- Realtime mode is provided by `skills/ai/audio/aliyun-qwen-tts-realtime/`.
107	- Voice cloning/design are provided by `skills/ai/audio/aliyun-qwen-tts-voice-clone/` and `skills/ai/audio/aliyun-qwen-tts-voice-design/`.
108
109	- Source list: `references/sources.md`

People who liked this also viewed

6 picks

Type