aliyun-qwen-tts-realtime

Name: aliyun-qwen-tts-realtime
Author: cinience

53installs34forks

How to install aliyun-qwen-tts-realtime?

cinience/alicloud-skills/aliyun-qwen-tts-realtime

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

Installs into the current project.

Summary

Use when real-time speech synthesis is needed with Alibaba Cloud Model Studio Qwen TTS Realtime models. Use when low-latency interactive speech is required, including instruction-controlled realtime synthesis.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen TTS Realtime
4
5	Use realtime TTS models for low-latency streaming speech output.
6
7	## Critical model names
8
9	Use one of these exact model strings:
10	- `qwen3-tts-flash-realtime`
11	- `qwen3-tts-instruct-flash-realtime`
12	- `qwen3-tts-instruct-flash-realtime-2026-01-22`
13	- `qwen3-tts-vd-realtime-2026-01-15`
14	- `qwen3-tts-vc-realtime-2026-01-15`
15
16	## Prerequisites
17
18	- Install SDK in a virtual environment:
19
20	```bash
21	python3 -m venv .venv
22	. .venv/bin/activate
23	python -m pip install dashscope
24	```
25	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
26
27	## Normalized interface (tts.realtime)
28
29	### Request
30	- `text` (string, required)
31	- `voice` (string, required)
32	- `instruction` (string, optional)
33	- `sample_rate` (int, optional)
34
35	### Response
36	- `audio_base64_pcm_chunks` (array<string>)
37	- `sample_rate` (int)
38	- `finish_reason` (string)
39
40	## Operational guidance
41
42	- Use websocket or streaming endpoint for realtime mode.
43	- Keep each utterance short for lower latency.
44	- For instruction models, keep instruction explicit and concise.
45	- Some SDK/runtime combinations may reject realtime model calls over `MultiModalConversation`; use the probe script below to verify compatibility.
46
47	## Local demo script
48
49	Use the probe script to verify realtime compatibility in your current SDK/runtime, and optionally fallback to a non-realtime model for immediate output:
50
51	```bash
52	.venv/bin/python skills/ai/audio/aliyun-qwen-tts-realtime/scripts/realtime_tts_demo.py \
53	--text "This is a realtime speech demo." \
54	--fallback \
55	--output output/ai-audio-tts-realtime/audio/fallback-demo.wav
56	```
57
58	Strict mode (for CI / gating):
59
60	```bash
61	.venv/bin/python skills/ai/audio/aliyun-qwen-tts-realtime/scripts/realtime_tts_demo.py \
62	--text "realtime health check" \
63	--strict
64	```
65
66	## Output location
67
68	- Default output: `output/ai-audio-tts-realtime/audio/`
69	- Override base dir with `OUTPUT_DIR`.
70
71	## Validation
72
73	```bash
74	mkdir -p output/aliyun-qwen-tts-realtime
75	for f in skills/ai/audio/aliyun-qwen-tts-realtime/scripts/*.py; do
76	python3 -m py_compile "$f"
77	done
78	echo "py_compile_ok" > output/aliyun-qwen-tts-realtime/validate.txt
79	```
80
81	Pass criteria: command exits 0 and `output/aliyun-qwen-tts-realtime/validate.txt` is generated.
82
83	## Output And Evidence
84
85	- Save artifacts, command outputs, and API response summaries under `output/aliyun-qwen-tts-realtime/`.
86	- Include key parameters (region/resource id/time range) in evidence files for reproducibility.
87
88	## Workflow
89
90	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
91	2) Run one minimal read-only query first to verify connectivity and permissions.
92	3) Execute the target operation with explicit parameters and bounded scope.
93	4) Verify results and save output/evidence files.
94
95	## References
96
97	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-qwen-tts-realtime

53installs34forks

View on GitHub

How to install aliyun-qwen-tts-realtime?

cinience/alicloud-skills/aliyun-qwen-tts-realtime

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen TTS Realtime
4
5	Use realtime TTS models for low-latency streaming speech output.
6
7	## Critical model names
8
9	Use one of these exact model strings:
10	- `qwen3-tts-flash-realtime`
11	- `qwen3-tts-instruct-flash-realtime`
12	- `qwen3-tts-instruct-flash-realtime-2026-01-22`
13	- `qwen3-tts-vd-realtime-2026-01-15`
14	- `qwen3-tts-vc-realtime-2026-01-15`
15
16	## Prerequisites
17
18	- Install SDK in a virtual environment:
19
20	```bash
21	python3 -m venv .venv
22	. .venv/bin/activate
23	python -m pip install dashscope
24	```
25	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
26
27	## Normalized interface (tts.realtime)
28
29	### Request
30	- `text` (string, required)
31	- `voice` (string, required)
32	- `instruction` (string, optional)
33	- `sample_rate` (int, optional)
34
35	### Response
36	- `audio_base64_pcm_chunks` (array<string>)
37	- `sample_rate` (int)
38	- `finish_reason` (string)
39
40	## Operational guidance
41
42	- Use websocket or streaming endpoint for realtime mode.
43	- Keep each utterance short for lower latency.
44	- For instruction models, keep instruction explicit and concise.
45	- Some SDK/runtime combinations may reject realtime model calls over `MultiModalConversation`; use the probe script below to verify compatibility.
46
47	## Local demo script
48
49	Use the probe script to verify realtime compatibility in your current SDK/runtime, and optionally fallback to a non-realtime model for immediate output:
50
51	```bash
52	.venv/bin/python skills/ai/audio/aliyun-qwen-tts-realtime/scripts/realtime_tts_demo.py \
53	--text "This is a realtime speech demo." \
54	--fallback \
55	--output output/ai-audio-tts-realtime/audio/fallback-demo.wav
56	```
57
58	Strict mode (for CI / gating):
59
60	```bash
61	.venv/bin/python skills/ai/audio/aliyun-qwen-tts-realtime/scripts/realtime_tts_demo.py \
62	--text "realtime health check" \
63	--strict
64	```
65
66	## Output location
67
68	- Default output: `output/ai-audio-tts-realtime/audio/`
69	- Override base dir with `OUTPUT_DIR`.
70
71	## Validation
72
73	```bash
74	mkdir -p output/aliyun-qwen-tts-realtime
75	for f in skills/ai/audio/aliyun-qwen-tts-realtime/scripts/*.py; do
76	python3 -m py_compile "$f"
77	done
78	echo "py_compile_ok" > output/aliyun-qwen-tts-realtime/validate.txt
79	```
80
81	Pass criteria: command exits 0 and `output/aliyun-qwen-tts-realtime/validate.txt` is generated.
82
83	## Output And Evidence
84
85	- Save artifacts, command outputs, and API response summaries under `output/aliyun-qwen-tts-realtime/`.
86	- Include key parameters (region/resource id/time range) in evidence files for reproducibility.
87
88	## Workflow
89
90	1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
91	2) Run one minimal read-only query first to verify connectivity and permissions.
92	3) Execute the target operation with explicit parameters and bounded scope.
93	4) Verify results and save output/evidence files.
94
95	## References
96
97	- `references/sources.md`

People who liked this also viewed

6 picks

Type