What is realtime-speech?

A development workflow for adding live speech-to-text and recording to browser applications using Azure AI Speech. It sends microphone audio from the browser to the speech service and receives text while the person is speaking.

Use it to build streaming transcription in Code Apps or similar browser apps, record audio, issue short-lived access tokens, and verify the feature on devices and hosted environments.

It addresses browser restrictions, low-latency audio delivery, temporary authentication, content-security rules, and testing across devices and real hosts.

How geekfujiwara/CodeAppsDevelopmentStandard configures Claude Code an

Reuse

Borrowing it

Nothing to install: this file belongs to geekfujiwara/CodeAppsDevelopmentStandard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/geekfujiwara/CodeAppsDevelopmentStandard/main/.github/skills/realtime-speech/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/geekfujiwara/CodeAppsDevelopmentStandard

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/realtime-speech/github.svg)](https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/realtime-speech)

Your own site

<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/realtime-speech"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/realtime-speech/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/realtime-speech"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/realtime-speech.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,100 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00152	$0.03100
Opus 5.5	$0.00061	$0.01240
Sonnet 5.5	$0.00030	$0.00620
Haiku 4.5	$0.00015	$0.00310

Measured 1mo ago against content hash dfea0b542e98, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

realtime-speech 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 1mo ago.

The scan reads SKILL.md. This mod also ships 16 executable files (scripts/get_speech_token.ps1, scripts/synthesize_script_wav.ps1, scripts/verify_push_stream.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.github/skills/realtime-speech/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

リアルタイム音声文字起こしスキル

ブラウザアプリ（主に Code Apps）で、話している内容をその場で文字にしながら録音する機能を作る。

マイク ─▶ AudioContext ─▶ AudioWorklet（同一オリジン）─▶ 16 kHz PCM ─▶ Push ストリーム ─▶ Speech SDK ─(WebSocket)─▶ Azure AI Speech
   └────▶ MediaRecorder（録音・opus）                                                              ▲ 短期トークン
Code Apps ─(カスタム コネクタ)─▶ トークン発行 Function（Managed Identity）────────────────────────────┘

判断	理由
ブラウザから Speech へ直結する	途中結果を 0.2〜0.4 秒間隔で受け取れる。サーバー中継は遅延と運用が増える
トークンはコネクタ経由の Function から受け取る	キーをブラウザに置かない（キー認証が無効なテナントでも動く）。コネクタ呼び出しは CSP の追加が不要
音声は自前で PCM にして Push ストリームで渡す	SDK にマイクを直接渡すと、Code Apps では音声が SDK に届かない

リファレンス: 認証とロール / 遅延と精度 / 連続録音の区切り / 名乗りからの話者の特定 / MAI-Transcribe との組み合わせ / 異常系 / パラメータ

Step 0: 事前確認（会話の最初に 1 回だけ）

standard の共通契約に加え、1 回の AskUserQuestion で確認する。

#	質問	合格条件
1	Speech リソースのサブスクリプション・リージョン・既存リソースの有無	リージョンが決まり、カスタムサブドメインを付けられる
2	環境の CSP に `connect-src wss://<region>.stt.speech.microsoft.com` を追加してよいか	CSP は環境全体に効く。変更の承認者が決まっている
3	ロール付与・コネクタ作成・DLP 分類の担当者	Azure RBAC、Power Platform のコネクタ、DLP の担当が分かれて記録されている
4	音声と文字起こしのデータ分類・保存期間・保存先	録音を扱ってよい根拠と保存先が決まっている
5	利用端末と会場（マイク、ブラウザ、ほかに動かすアプリ）	端末の負荷とマイクの経路（ミキサー等）が分かっている

Step 1: Speech リソースと権限を用意する

Speech リソース（kind=SpeechServices）をカスタムサブドメイン付きで作る。キー認証が無効でもよい（Entra ID で認証する）
開発者とトークン発行 Function の Managed Identity に Foundry User を付ける。Managed Identity はリソースグループの範囲で付ける（実測で数秒〜2 分で反映。リソース範囲は反映に約 12 分かかった。通らなかったロールは認証とロール）

Step 2: 端末で往復検証する

アプリを作る前に、リソース・権限・リージョンが正しいことを端末だけで確かめる。 Speech SDK を入れたプロジェクトのフォルダーで実行する。

$env:SPEECH_TOKEN = (powershell -File .github/skills/realtime-speech/scripts/get_speech_token.ps1 -Raw)
node .github/skills/realtime-speech/scripts/verify_speech_roundtrip.mjs --out samples/question.wav --phrase <専門用語>
node .github/skills/realtime-speech/scripts/verify_push_stream.mjs --wav samples/question.wav

Read the full file on GitHub · 150 lines

Files

What ships with it

35 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.

Changes

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.

1mo ago First seen · 150 lines · 152 tokens per session scan A dfea0b542e98

Subscribe to this mod's changes

realtime-speech is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (78 stars, last pushed yesterday), licensed MIT. It adds 152 tokens to every session and 3,100 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-03.

Frontend ai

realtime-speech next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
realtime-speechgeekfujiwara/CodeAppsDevelopmentStandard	Skill	78	yesterday	MIT	A	152	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

CodeAppsDevelopmentStandard: Skill for Claude Code