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 agentmods add skills/skills-il/developer-tools/hebrew-voice-bot-buildernpx skills add skills-il/developer-tools --skill hebrew-voice-bot-buildergit clone --depth 1 https://github.com/skills-il/developer-toolsWrote 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/skills-il/developer-tools/hebrew-voice-bot-builder)<a href="https://agentmods.dev/skills/skills-il/developer-tools/hebrew-voice-bot-builder"><img src="https://agentmods.dev/badge/skills/skills-il/developer-tools/hebrew-voice-bot-builder.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00192 | $0.09747 |
| Opus 5 | $0.00096 | $0.04874 |
| Sonnet 5 | $0.00038 | $0.01949 |
| Haiku 4.5 | $0.00019 | $0.00975 |
Grade A, and why
hebrew-voice-bot-builder 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 6d 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 — 811 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hebrew Voice Bot Builder
Build production-ready Hebrew voice bots and IVR systems for Israeli businesses. This skill covers the full voice pipeline: speech-to-text (STT), text-to-speech (TTS), IVR flow design, telephony integration, and Hebrew-specific challenges like accent handling and mixed Hebrew-English speech.
Instructions
Language code: Google STT uses
iw-IL, Google TTS useshe-IL. Google's Speech-to-Text supported-languages table lists Hebrew asiw-IL(the legacy ISO code for Hebrew), while the Text-to-Speech voice list useshe-IL(he-IL-Wavenet-A,he-IL-Chirp3-HD-*). Pass the documented code for each side rather than assuming one code works for both.
Step 1: Choose Your Architecture
Before building, decide on the voice bot architecture based on the use case:
| Architecture | Best For | Components |
|---|---|---|
| IVR (keypad) | Simple menu navigation, payment lines, appointment scheduling | TTS + DTMF + telephony |
| Voice bot (conversational) | Customer service, order status, FAQ handling | STT + LLM + TTS + telephony |
| Voicemail transcription | Missed call handling, message routing | STT + notification pipeline |
| Hybrid | Complex flows with both speech and keypad input | STT + TTS + DTMF + telephony |
Key decisions:
- STT provider: OpenAI
gpt-4o-transcribeorgpt-4o-mini-transcribe(lower latency thanwhisper-1and available via the OpenAI Realtime API for streaming),whisper-large-v3-turbofor self-host, ivrit-ai's Hebrew-tuned variants (ivrit-ai/whisper-large-v3-turbo-ct2) for an open model trained specifically on Hebrew, Google Cloud STT (low latency; Hebrew runs on Chirp,iw-IL), Azure Speech (enterprise features), and ElevenLabs Scribe v2, which lists Hebrew (heb) in the "Good (>10% to <=20% WER)" band with a realtime variant at roughly 150ms. Note the WER band honestly: Hebrew is two tiers below English there, so benchmark on your own call audio rather than picking on the marketing claim. The legacywhisper-1API is still supported butgpt-4o-transcribeis the current default for Hebrew. - TTS provider, split by use case:
- Real-time / streaming (voice agents, IVR, live conversation): OpenAI Realtime API, native multilingual speech-to-speech including Hebrew over WebRTC/WebSocket/SIP, the 2026 default for sub-500ms turn-taking. The current GA model is
gpt-realtime-2.1(gpt-realtime-2.1-minifor the smaller tier). Two model names to avoid:gpt-realtimewas deprecated on 2026-07-20 with a hard shutdown on 2027-01-20 (replacementgpt-realtime-2.1), andgpt-4o-realtime-previewwas removed from the API on 2026-05-07.gpt-realtime-1.5is still live. Other realtime options: ElevenLabseleven_v3_conversational(~280ms, and Hebrew IS in the v3 language list, so this is now a real realtime-Hebrew route), Inworld Realtime TTS-2 and TTS-2 Flash (Inworld advertises "200+ languages" but does NOT enumerate Hebrew in its docs, so treat Hebrew as untested there and verify with your own audio; the older TTS-1 / TTS-1.5 names no longer appear), and Deepdub Phantom X 3.2 from the Israeli vendor Deepdub. Do NOT reach for ElevenLabseleven_flash_v2_5for Hebrew: its language list is Multilingual v2's 29 languages plus Hungarian, Norwegian and Vietnamese, so Hebrew is absent entirely rather than merely weak. - Offline / max quality (audiobooks, voicemail playback, batch generation): ElevenLabs
eleven_v3, best Hebrew quality ElevenLabs offers, supports Hebrew (heb) among 70+ languages but NO WebSocket / streaming API, REST only. Deepdub Phantom X 3.2 also serves this track with emotional control. - Fallbacks: Azure Neural TTS (
he-IL-HilaNeural,he-IL-AvriNeural), Google Cloud TTS Wavenet (he-IL-Wavenet-A/B). Amazon Polly does NOT support Hebrew (no he-IL locale, no Hebrew voice of any engine, the "Avri" voice belongs to Azure, not Polly), so do not route Hebrew through Polly. ElevenLabs Multilingual v2 does NOT list Hebrew: its documented 29 languages are en, ja, zh, de, hi, fr, ko, pt, it, es, id, nl, tr, fil, pl, sv, bg, ro, ar, cs, el, fi, hr, ms, sk, da, ta, uk and ru. Hebrew appears only in the Eleven v3 language list, so route Hebrew to v3 (or to Azure/Google above) and not to Multilingual v2.
- Real-time / streaming (voice agents, IVR, live conversation): OpenAI Realtime API, native multilingual speech-to-speech including Hebrew over WebRTC/WebSocket/SIP, the 2026 default for sub-500ms turn-taking. The current GA model is
- Telephony: Twilio and Vonage both sell Israeli numbers. Twilio publishes Israeli voice pricing (local, mobile and toll-free tiers); Vonage does not publish comparable Israeli number documentation, so compare quotes yourself rather than trusting a ranking. Number portability exists in the Israeli market, but confirm with the carrier that your specific number can be ported to your chosen provider before committing.
- Hosting: Cloud functions for low-volume, dedicated servers for high-volume.
- Call recording and voiceprints: play a recording announcement (
השיחה מוקלטת) at the start of the call. It is standard practice for Israeli call flows, and this skill does not assert it as a cited statutory duty (an earlier version did, and the source did not hold up). Treat a voiceprint as a different artifact from the recording: store it in its own table, keyed for per-caller deletion, so it can be erased independently of the audio and of the transcript. Have the operator confirm which obligations apply to their business with a qualified professional before launch.
What ships with it
7 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.
- 6d ago First seen · 811 lines · 192 tokens per session scan A 58af21d4b3b5
hebrew-voice-bot-builder is a skill published in the GitHub repository skills-il/developer-tools (10 stars, last pushed 4d ago), licensed MIT. It adds 192 tokens to every session and 9,747 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
heygen
Prepare guarded HeyGen Direct API requests for avatar video generation, video translation, asset discovery, and status polling.
webiny-v5-to-v6-migration
Migration patterns for converting v5 Webiny code to v6 architecture. Use this skill when migrating existing v5 plugins to v6 features, converting context plugins to DI services, adapting v5 event subscriptions to v6 EventHandlers, or understanding how v5 patterns translate to v6. Targeted at AI agents performing…
contentful-cms
Creates Contentful content types, queries entries via GraphQL/REST, runs CLI migrations, and manages assets and locales. Use when building or modifying Contentful content models, writing queries, or migrating content.
backend-internationalization
Use this skill when implementing multi-language support, translation workflows, or locale-aware formatting. This skill enforces: BCP 47 locale tags, ICU MessageFormat for complex messages, dot-separated namespaced keys, fallback chains, and CI-validated translation files. Applies to any backend stack serving…
polylang-rest-headless
Build or audit REST and headless integrations with Polylang 3.8.5, Polylang Pro 3.8.5, and Polylang for WooCommerce 2.2.2. Covers REST lang parameter behavior, pll/v1 languages, filterable REST routes, Pro lang/translations REST fields, pllrestapiposttypes and pllrestapitaxonomies 3.8 format, pll/v1/translation and…
fec-data-fetching
用于实现或审查前端服务端状态流程:类型化查询、请求缓存、失效、mutation、乐观更新、无限查询、预取、SSR hydration 或 API 层整合。不要用于本地 UI 状态或 Service Worker 缓存;中文触发词包括 数据获取、缓存、乐观更新。.