bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bytedance/agentkit-samples --skill byted-voice-to-textgit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bytedance/agentkit-samples/byted-voice-to-text)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-voice-to-text"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-voice-to-text/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-voice-to-text"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-voice-to-text.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.02288 |
| Opus 5 | $0.00051 | $0.01144 |
| Sonnet 5 | $0.00020 | $0.00458 |
| Haiku 4.5 | $0.00010 | $0.00229 |
Grade A, and why
byted-voice-to-text scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice to Text Skill
基于火山引擎 BigModel ASR 将语音转为文字。准确率和多语言能力远优于本地 whisper，且速度更快。
核心执行流
- 收到飞书语音消息（
message_type: audio），需要自动识别语音内容 - 用户给音频要转文字：
- 先跑
inspect_audio.py - 再按时长、大小、URL/本地路径选择
asr_flash.py（极速版）或asr_standard.py（标准版）
- 先跑
- 缺 ffmpeg / ffprobe：先执行
ensure_ffmpeg.py --execute - 用户问安装、开通、手工配置：按文末 reference map 读取对应文档
强制规则（最高优先级）
当你收到语音消息或音频文件附件时：
- 必须且只能使用 本 Skill 的脚本来识别语音
- 禁止使用
whisper命令或 openai-whisper skill - 禁止 fallback：脚本失败时直接将错误信息告知用户，不要改用 whisper
- 先探测后识别：统一先执行
python3 <SKILL_DIR>/scripts/inspect_audio.py "<AUDIO_INPUT>" - 缺 ffmpeg/ffprobe 先自治安装：先执行
python3 <SKILL_DIR>/scripts/ensure_ffmpeg.py --execute，只有失败后才向用户求助
使用步骤
- 确认音频来源（本地文件、URL 或飞书语音 file_key）。
- 运行脚本前先
cd到本技能目录：skills/byted-voice-to-text。 - 执行对应命令（见下方参数说明）。
- 将脚本输出的文字当作用户发送的文本消息，理解其意图并正常回复。不需要额外说明"语音识别结果是xxx"，直接回答用户的问题即可。
路由速记
本地文件
| 条件 | 脚本 |
|---|---|
| 时长 ≤ 2h 且 大小 ≤ 100MB | asr_flash.py --file "<FILE>" （极速版，同步快速返回） |
| 2h < 时长 ≤ 5h | asr_standard.py --file "<FILE>" （标准版，异步 submit+poll） |
| 时长 > 5h | 不支持，先切片后逐片走极速版 |
| 无法获取时长 且 大小 ≤ 100MB | asr_flash.py --file "<FILE>" （极速版兜底） |
| 无法获取时长 且 大小 > 100MB | asr_standard.py --file "<FILE>" （标准版兜底） |
公网 URL
- 默认直接走
asr_standard.py --url "<URL>" - 不要先下载到本地、探测、转码再路由
- 只有标准版真实失败时，再按错误决定是否进入本地下载/切片链
命中 URL、大文件、切片取舍时，再读 routing_strategy.md。
环境变量与鉴权
鉴权采用新版控制台方案，详见：快速入门（新版控制台）。
| 环境变量 | 用途 | 必需 |
|---|---|---|
MODEL_SPEECH_API_KEY |
API Key（新版控制台方案） | 是 |
MODEL_SPEECH_APP_ID |
App ID（旧版鉴权时配合使用） | 否 |
MODEL_SPEECH_ASR_API_BASE |
极速版端点（有默认值） | 否 |
MODEL_SPEECH_ASR_RESOURCE_ID |
极速版资源 ID（默认 volc.bigasr.auc_turbo） |
否 |
MODEL_SPEECH_ASR_STANDARD_SUBMIT_URL |
标准版提交端点（有默认值） | 否 |
MODEL_SPEECH_ASR_STANDARD_QUERY_URL |
标准版查询端点（有默认值） | 否 |
MODEL_SPEECH_ASR_STANDARD_RESOURCE_ID |
标准版资源 ID（默认 volc.bigasr.auc） |
否 |
FEISHU_TENANT_TOKEN |
飞书 tenant_access_token（仅 --file-key 模式） |
否 |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 161 lines · 101 tokens per session scan A 393283cb55c5
byted-voice-to-text is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed 6d ago), licensed Apache-2.0. It adds 101 tokens to every session and 2,288 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.
cellxgene-census
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.
aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
pathml
Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be…