siliconflow-qwen-asr

语音转文字技能（SiliconFlow优先，Qwen ASR兜底）。当需要处理语音消息、语音附件、音频文件或音频URL并提取可读文本时使用。支持本地音频与公网URL输入，默认先调用SiliconFlow /audio/transcriptions，失败后自动回退到Qwen3-ASR-Flash。

Ir para a instalação

Repositório: justcyl/my-skills
Última atividade na origem: 6 de março de 2026 às 07:28
Idioma detectado do SKILL.md: chinês
Estrelas: 0
Forks: 0

Opções de instalação

Por padrão, está selecionado o prompt que primeiro revisa a origem. Você pode mudar para um comando direto ou baixar uma cópia local.

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.

npx skills add https://github.com/justcyl/my-skills --skill siliconflow-qwen-asr

O comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.

Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.

Revise os arquivos de origem

Leia o SKILL.md e os arquivos complementares exibidos pelo SkillsMP antes de decidir se vai instalar.

Explorador de arquivos

3 arquivos

SKILL.md

Instruções da origem · Visualização somente leitura

Voltar à pesquisa Voltar à instalação

image-gen-kapibala

使用 Kapibala 的 OpenAI 兼容图片接口生成/编辑位图图片，默认模型 gpt-image-2。当需要生成图片、编辑已有图片、或批量生成候选图供挑选时触发。触发词："生成图片""画一张""image generation""edit this image""gpt-image-2""批量出图"。

2026-09-07

add-svg

Add, collect, design, audit, and integrate SVG elements into editable diagrams.net/draw.io scientific figures. Use when the user asks to supplement a draw.io diagram with SVG icons, mechanisms, biological objects, model components, pathway symbols, instruments, graphical abstract elements, or publication-style vector assets. Every execution must first ask the user to choose the SVG source mode: network search or self-designed SVG. For network mode, search for multiple relevant SVG candidates for later user selection, record sources and license notes, and fall back to self-designed SVG for concepts with no suitable result. For self-design mode, create restrained, editable, Nature-style SVGs from simple vector primitives. Use with .drawio, SVG, diagrams.net, 科研流程图, 论文示意图, SVG补图, 图标补充, and draw.io配图.

2026-09-04

research-draw

Two-stage workflow for publication-style scientific schematics: generate or use a raster reference with imagegen/PNG/JPG/WebP, then trace it into an editable diagrams.net/draw.io file using research-drawio-skill. Use for Nature-style scientific illustrations, graphical abstracts, model or mechanism schematics, biomedical workflows, AI architecture figures, and paper-style visual drafts that should become editable .drawio source. For complex recognizable elements, author or select dedicated SVG glyphs and compare rendered SVGs against reference crops before inserting them, instead of assembling those elements from draw.io primitives. Enforces a minimum three-round strict pixel-level export/compare/fix loop for close raster-to-draw.io tracing tasks. Use with imagegen, draw.io, diagrams.net, scientific illustration, graphical abstract, paper schematic, figure tracing, SVG glyph tracing, and drawio redraw requests.

2026-09-04

Ver todas deste repositório

SiliconFlow + Qwen ASR

使用 scripts/transcribe.py 做统一转写入口：

默认：SiliconFlow 优先，失败自动 fallback 到 Qwen

可强制指定 provider

输入支持本地文件或 URL

快速开始

# 1) 安装依赖 pip install requests # 2) 配置密钥（建议都配） export SILICONFLOW_API_KEY="sk-..." export DASHSCOPE_API_KEY="sk-..." # 3) 自动模式（推荐） python scripts/transcribe.py /path/to/audio.mp3 python scripts/transcribe.py "https://example.com/audio.mp3"

常用命令

# 强制仅用 SiliconFlow python scripts/transcribe.py audio.mp3 --provider siliconflow # 强制仅用 Qwen python scripts/transcribe.py audio.mp3 --provider qwen # Qwen 国际站 python scripts/transcribe.py audio.mp3 --provider qwen --qwen-region intl # Qwen 指定语种 + ITN python scripts/transcribe.py audio.mp3 --provider qwen --language zh --enable-itn

在会话中处理语音消息的流程

拿到语音文件路径或语音URL。

执行：python scripts/transcribe.py <audio>。

将输出文本直接用于总结、翻译、提炼行动项。

若日志出现 [WARN] SiliconFlow失败，表示已自动回退到Qwen并继续处理。

关键参数

--provider auto|siliconflow|qwen：选择调用策略（默认 auto）

--sf-model：SiliconFlow模型（默认 FunAudioLLM/SenseVoiceSmall）

--qwen-model：Qwen模型（默认 qwen3-asr-flash）

--qwen-region cn|intl：Qwen地域

--language：Qwen已知语种时可指定

--enable-itn：Qwen数字/日期规范化（中英文更有用）

参考资料

name	siliconflow-qwen-asr
description	语音转文字技能（SiliconFlow优先，Qwen ASR兜底）。当需要处理语音消息、语音附件、音频文件或音频URL并提取可读文本时使用。支持本地音频与公网URL输入，默认先调用SiliconFlow /audio/transcriptions，失败后自动回退到Qwen3-ASR-Flash。