aliyun-qwen-asr-realtime

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

53installs34forks

How to install aliyun-qwen-asr-realtime?

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

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

Installs into the current project.

Summary

Use when low-latency realtime speech recognition is needed with Alibaba Cloud Model Studio Qwen ASR Realtime models, including streaming microphone input, live captions, or duplex voice agents.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen ASR Realtime
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-qwen-asr-realtime
9	python -m py_compile skills/ai/audio/aliyun-qwen-asr-realtime/scripts/prepare_realtime_asr_request.py && echo "py_compile_ok" > output/aliyun-qwen-asr-realtime/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-qwen-asr-realtime/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save session payloads and response samples under `output/aliyun-qwen-asr-realtime/`.
17
18	## Critical model names
19
20	Use one of these exact model strings:
21	- `qwen3-asr-flash-realtime`
22	- `qwen3-asr-flash-realtime-2026-02-10`
23
24	## Use cases
25
26	- Realtime subtitles and captions
27	- Voice-agent duplex input
28	- Streaming speech-to-text in browser or terminal clients
29
30	## Prerequisites
31
32	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
33	- Realtime sessions generally require WebSocket or streaming session handling in the client.
34
35	## Normalized interface (asr.realtime)
36
37	### Request
38	- `model` (string, optional): default `qwen3-asr-flash-realtime`
39	- `language_hints` (array<string>, optional)
40	- `format` (string, optional): e.g. `pcm`, `wav`
41	- `sample_rate` (int, optional): e.g. `16000`
42	- `chunk_ms` (int, optional): frame size in milliseconds
43
44	### Response
45	- `text` (string): recognized transcript fragment
46	- `is_final` (bool): finalization marker
47	- `usage` (object, optional)
48
49	## Quick start
50
51	Generate a request template:
52
53	```bash
54	python skills/ai/audio/aliyun-qwen-asr-realtime/scripts/prepare_realtime_asr_request.py \
55	--output output/aliyun-qwen-asr-realtime/request.json
56	```
57
58	## Operational guidance
59
60	- Prefer 16kHz mono PCM unless your client stack requires another format.
61	- Keep chunks small enough for responsive partial results.
62	- If you only have recorded files, use `skills/ai/audio/aliyun-qwen-asr/` instead.
63
64	## References
65
66	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-qwen-asr-realtime

53installs34forks

View on GitHub

How to install aliyun-qwen-asr-realtime?

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

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

Installs into the current project.

Summary

Use when low-latency realtime speech recognition is needed with Alibaba Cloud Model Studio Qwen ASR Realtime models, including streaming microphone input, live captions, or duplex voice agents.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio Qwen ASR Realtime
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-qwen-asr-realtime
9	python -m py_compile skills/ai/audio/aliyun-qwen-asr-realtime/scripts/prepare_realtime_asr_request.py && echo "py_compile_ok" > output/aliyun-qwen-asr-realtime/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-qwen-asr-realtime/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save session payloads and response samples under `output/aliyun-qwen-asr-realtime/`.
17
18	## Critical model names
19
20	Use one of these exact model strings:
21	- `qwen3-asr-flash-realtime`
22	- `qwen3-asr-flash-realtime-2026-02-10`
23
24	## Use cases
25
26	- Realtime subtitles and captions
27	- Voice-agent duplex input
28	- Streaming speech-to-text in browser or terminal clients
29
30	## Prerequisites
31
32	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
33	- Realtime sessions generally require WebSocket or streaming session handling in the client.
34
35	## Normalized interface (asr.realtime)
36
37	### Request
38	- `model` (string, optional): default `qwen3-asr-flash-realtime`
39	- `language_hints` (array<string>, optional)
40	- `format` (string, optional): e.g. `pcm`, `wav`
41	- `sample_rate` (int, optional): e.g. `16000`
42	- `chunk_ms` (int, optional): frame size in milliseconds
43
44	### Response
45	- `text` (string): recognized transcript fragment
46	- `is_final` (bool): finalization marker
47	- `usage` (object, optional)
48
49	## Quick start
50
51	Generate a request template:
52
53	```bash
54	python skills/ai/audio/aliyun-qwen-asr-realtime/scripts/prepare_realtime_asr_request.py \
55	--output output/aliyun-qwen-asr-realtime/request.json
56	```
57
58	## Operational guidance
59
60	- Prefer 16kHz mono PCM unless your client stack requires another format.
61	- Keep chunks small enough for responsive partial results.
62	- If you only have recorded files, use `skills/ai/audio/aliyun-qwen-asr/` instead.
63
64	## References
65
66	- `references/sources.md`

People who liked this also viewed

6 picks

Type