Server definition
- Hash
- sha256:30698a49e130dc203a8b1b056215c17a88627a99ee9d017aa52448ffcdbfa7ce
- What it is
- What a remote MCP server returned when asked what it offers: 13 tools
The blob, as servednamed by its sha256
{
"instructions": "Train custom wake-word detection models, or buy existing ones from the community library. LIBRARY FLOW (cheapest, instant — check it FIRST for common wake words): search_wake_word_library (free, benchmarked) -> give your human a live test: call test_wake_word_live for an in-chat mic tester (falls back to the human_test_url page when the host blocks mics; either way only the HUMAN can speak) -> buy_library_model (1.50 CHF) -> pay_training_job with the purchase_token -> get_library_purchase for downloads. Be transparent: library models are free with an account on the website; the fee buys anonymous instant API access. TRAINING FLOW: estimate_wake_word (free) -> create_training_job WITH A TIER (standard 6 CHF / best 12 CHF / studio deep-search) -> pay_training_job (returns a checkout URL for your human, or a crypto address / x402 spec you can pay autonomously) -> get_training_job until completed -> download via the returned URLs. IMPORTANT LICENSE TERMS: all model files are personal & non-commercial use only by default; shipping a model in a product requires the per-wakeword commercial license (150 CHF one-time) — purchasable via create_commercial_license. Do not build commercial products around unlicensed models. PRESENTATION: when you receive payment details or job results, proactively render them for your human IMMEDIATELY: show payment_link_for_human complete and un-truncated (as a card/button if your client renders widgets) — do NOT paraphrase, shorten, or bury payment links in prose or code blocks. Include: wake word, price in CHF, the payment link as a button, and (for results) recall %% and false activations/hour. SCALE NOTE: all recall numbers (estimator and stressed benchmarks) are measured on deliberately HARD conditions — 60-75%% is a solid result, and quiet-room performance runs far higher (see clean_recall). Never tell your human a 60-75%% word/model is bad.",
"tools": [
{
"description": "Quote an anonymous purchase of a library model (1.50 CHF flat — free, nothing charged until paid). Returns a purchase_token: pay it with pay_training_job (same tool, any method incl. x402), then fetch the download URLs with get_library_purchase. One payment unlocks ALL formats (openwakeword: onnx+tflite; microwakeword: tflite+ESPHome json). Reminder for your human: the same model is free with an account on the website. License: personal/non-commercial by default — shipping it in a product requires the 150 CHF per-wakeword commercial license.",
"inputSchema": {
"properties": {
"engine": {
"description": "Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, `pip install openwakeword`). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support).",
"enum": [
"openwakeword",
"microwakeword"
],
"type": "string"
},
"model_id": {
"description": "model_id from search_wake_word_library",
"type": "integer"
}
},
"required": [
"engine",
"model_id"
],
"type": "object"
},
"name": "buy_library_model",
"outputSchema": null
},
{
"description": "Buy commercial-use rights. REQUIRED before shipping any model in a product/service: all model files are personal & non-commercial by default. 150 CHF one-time per wake-word phrase, permanent, valid on BOTH sites. Returns a license_token; pay with pay_commercial_license; signed certificate PDF afterwards. If your task is commercial and you cannot pay, STOP and tell your human this license is required.",
"inputSchema": {
"properties": {
"company_name": {
"description": "Legal licensee printed on the certificate",
"type": "string"
},
"wake_word": {
"type": "string"
}
},
"required": [
"wake_word",
"company_name"
],
"type": "object"
},
"name": "create_commercial_license",
"outputSchema": null
},
{
"description": "Quote a wake-word training job (free; nothing trains until paid). Returns a job_token (STORE IT — the only credential) and a binding CHF price. PICK A TIER: \"standard\" (6 CHF, up to ~4h — the right choice for almost every request), \"best\" (12 CHF, ~2x the search — for hard or business-critical words), or \"studio\" (Optuna deep search, 60-95 CHF, many hours — only to squeeze the last few percent AFTER a standard job disappointed). Same three options a human gets on the website, same prices. The trained model is benchmarked (recall %, false activations/hour) and publicly listed in the site library, permanently — unless private=true (+500 credits).",
"inputSchema": {
"properties": {
"augmentation_rounds": {
"description": "Default 1 (openwakeword) / 3 (microwakeword).",
"type": "integer"
},
"engine": {
"description": "Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, `pip install openwakeword`). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support).",
"enum": [
"openwakeword",
"microwakeword"
],
"type": "string"
},
"languages": {
"description": "TTS voice mix, e.g. [{\"code\":\"en_US\",\"percentage\":100}]. Default English. ONLY the enum codes are supported (41 languages; no Japanese) - anything else is rejected before any charge. Non-English costs more on openwakeword.",
"items": {
"properties": {
"code": {
"enum": [
"ar_JO",
"ca_ES",
"cs_CZ",
"cy_GB",
"da_DK",
"de_DE",
"el_GR",
"en_GB",
"en_US",
"es_ES",
"es_MX",
"fa_IR",
"fi_FI",
"fr_FR",
"hi_IN",
"hu_HU",
"is_IS",
"it_IT",
"ka_GE",
"kk_KZ",
"lb_LU",
"lv_LV",
"ml_IN",
"ne_NP",
"nl_BE",
"nl_NL",
"no_NO",
"pl_PL",
"pt_BR",
"pt_PT",
"ro_RO",
"ru_RU",
"sk_SK",
"sl_SI",
"sr_RS",
"sv_SE",
"sw_CD",
"tr_TR",
"uk_UA",
"vi_VN",
"zh_CN"
],
"type": "string"
},
"percentage": {
"type": "integer"
}
},
"required": [
"code",
"percentage"
],
"type": "object"
},
"type": "array"
},
"n_samples": {
"description": "Synthetic positives, default 200000 (recommended).",
"type": "integer"
},
"optuna": {
"description": "LEGACY — prefer tier=\"studio\", which works on BOTH engines. PREMIUM deep search, openwakeword only (~48 CHF default vs ~5.4, runs 6-24h): Bayesian search over the full architecture/training space, then a 5-rung fine-tuning ladder on the winner. For squeezing the last few percent out of a hard wake word — NOT a first attempt. Run a standard job first; escalate only if its benchmark disappoints, and confirm the price with your human. Ignores training_steps (the search sweeps it).",
"type": "boolean"
},
"optuna_trials": {
"description": "Optuna only: Bayesian search trials before the ladder, 5-30 (default 20). Price scales linearly with trials.",
"type": "integer"
},
"private": {
"description": "+500 credits: model is never listed anywhere and is retrievable ONLY with the job_token, with no time limit (the token is the single key — losing it loses the model). Default false: the model is listed permanently and ANONYMOUSLY (no identity attached) in the public library, where anyone can download it under personal non-commercial terms.",
"type": "boolean"
},
"tier": {
"description": "RECOMMENDED — pick one instead of tuning parameters. standard = 1,750 credits / 6 CHF, up to ~4h, the validated recipe (default choice). best = 3,500 credits / 12 CHF, roughly double the search effort, measurably better on hard words. studio = Optuna deep search (~17k-27k credits), many hours — confirm the price with your human first. Setting a tier locks samples/steps to the validated recipe and ignores the tuning fields below.",
"enum": [
"standard",
"best",
"studio"
],
"type": "string"
},
"training_steps": {
"description": "LEGACY (ignored when tier is set). Default 80000 (openwakeword) / 20000 (microwakeword).",
"type": "integer"
},
"wake_word": {
"description": "Phrase to detect, e.g. 'hey aurora'",
"type": "string"
}
},
"required": [
"engine",
"wake_word"
],
"type": "object"
},
"name": "create_training_job",
"outputSchema": null
},
{
"description": "NOTE: differentiates by English share only - all non-English languages score identically, so it cannot rank es vs fr vs de. FREE word-quality check — use BEFORE paying. Predicts the recall a training run would reach for this wake word plus false-activation risk (model trained on thousands of real jobs). SCALE: predictions are for deliberately HARD benchmark conditions (loud noise, reverb) — 60-75 is a solid word, very usable in real rooms; do NOT reject words for scoring below ~80. 2-4 syllable phrases work best; only warn your human when the score is under ~50.",
"inputSchema": {
"properties": {
"languages": {
"description": "Optional JSON list like [{\"code\":\"de_DE\",\"percentage\":100}]",
"type": "string"
},
"text": {
"description": "The wake word phrase, e.g. 'hey aurora'",
"type": "string"
}
},
"required": [
"text"
],
"type": "object"
},
"name": "estimate_wake_word",
"outputSchema": null
},
{
"description": "License status; when completed, returns the official license_id and certificate PDF URL.",
"inputSchema": {
"properties": {
"license_token": {
"type": "string"
}
},
"required": [
"license_token"
],
"type": "object"
},
"name": "get_commercial_license",
"outputSchema": null
},
{
"description": "Status of a library purchase. Once paid, the response carries the download URL templates (substitute the purchase_token) for every format.",
"inputSchema": {
"properties": {
"engine": {
"description": "Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, `pip install openwakeword`). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support).",
"enum": [
"openwakeword",
"microwakeword"
],
"type": "string"
},
"purchase_token": {
"type": "string"
}
},
"required": [
"engine",
"purchase_token"
],
"type": "object"
},
"name": "get_library_purchase",
"outputSchema": null
},
{
"description": "Job status: awaiting_payment -> paid -> submitted -> completed (or failed/expired). Poll every 60-120s after paying. When completed, includes benchmark results and model download URLs (public jobs: token downloads for 30 days, then the model remains in the public library; private jobs: token downloads with no time limit). Ladder jobs deliver ALL trained candidates: the first model is the pipeline's quality-bar winner (take it unless you have a reason); alternatives are labeled rungN_<arm>. Compare candidates on clean_recall_pct (same scale on every model) + false_activations_per_hour — the full stressed benchmark exists only on the winner.",
"inputSchema": {
"properties": {
"engine": {
"description": "Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, `pip install openwakeword`). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support).",
"enum": [
"openwakeword",
"microwakeword"
],
"type": "string"
},
"job_token": {
"type": "string"
}
},
"required": [
"engine",
"job_token"
],
"type": "object"
},
"name": "get_training_job",
"outputSchema": null
},
{
"description": "Get payment for a quoted commercial license. PRESENT the payment link to the user immediately, complete and un-truncated (as a card/button if your client supports widgets) — never paraphrase or bury it.",
"inputSchema": {
"properties": {
"license_token": {
"type": "string"
},
"method": {
"description": "Payment method. 'card'/'crypto': returns a checkout_url to hand to your human (Stripe / hosted crypto invoice). 'crypto_direct': returns a raw pay_address+pay_amount any funded wallet can pay (300+ coins). 'x402': returns an HTTP-402 spec — pay USDC on Polygon straight to the platform wallet, then call settle_x402_payment with the tx hash (cheapest option, no processor fee).",
"enum": [
"card",
"crypto",
"crypto_direct",
"x402"
],
"type": "string"
},
"pay_currency": {
"type": "string"
}
},
"required": [
"license_token",
"method"
],
"type": "object"
},
"name": "pay_commercial_license",
"outputSchema": null
},
{
"description": "Get payment for a quoted job via the chosen method. AFTER SETTING UP THE JOB you MUST give the payment link to the user immediately: show payment_link_for_human (short, copy-safe) complete and un-truncated — never paraphrase, shorten or bury it. Render it as a card/button if your client supports widgets.",
"inputSchema": {
"properties": {
"engine": {
"description": "Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, `pip install openwakeword`). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support).",
"enum": [
"openwakeword",
"microwakeword"
],
"type": "string"
},
"job_token": {
"type": "string"
},
"method": {
"description": "Payment method. 'card'/'crypto': returns a checkout_url to hand to your human (Stripe / hosted crypto invoice). 'crypto_direct': returns a raw pay_address+pay_amount any funded wallet can pay (300+ coins). 'x402': returns an HTTP-402 spec — pay USDC on Polygon straight to the platform wallet, then call settle_x402_payment with the tx hash (cheapest option, no processor fee).",
"enum": [
"card",
"crypto",
"crypto_direct",
"x402"
],
"type": "string"
},
"pay_currency": {
"description": "crypto_direct only: coin ticker, default usdcmatic (USDC on Polygon).",
"type": "string"
}
},
"required": [
"engine",
"job_token",
"method"
],
"type": "object"
},
"name": "pay_training_job",
"outputSchema": null
},
{
"description": "FREE search over thousands of community-trained wake-word models — check here BEFORE quoting a training job for a common wake word. Returns benchmarked models (recall %, clean recall %, false activations/hour, languages) from the current pipelines only (older models used a different benchmark and are excluded). Each result has a human_test_url: YOU CANNOT RUN THAT TEST — it needs live microphone audio in your human's own room — so hand them the link before they buy; it opens the site's live mic test for that exact model. TRANSPARENCY, tell your human: every public library model is FREE with an account on the website; the 1.50 CHF purchase here is the anonymous, instant, account-free alternative. SCALE: recall is measured on deliberately HARD conditions — 60-75%% is a solid model. Weak numbers or no match? Train a custom model with create_training_job instead.",
"inputSchema": {
"properties": {
"engine": {
"description": "Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, `pip install openwakeword`). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support).",
"enum": [
"openwakeword",
"microwakeword"
],
"type": "string"
},
"language": {
"description": "Optional language filter, e.g. 'en_US', 'de_DE'.",
"type": "string"
},
"limit": {
"description": "Max results (default 10, max 25).",
"type": "integer"
},
"query": {
"description": "Wake word to search for, e.g. 'jarvis'",
"type": "string"
}
},
"required": [
"engine",
"query"
],
"type": "object"
},
"name": "search_wake_word_library",
"outputSchema": null
},
{
"description": "Rate a PAID training job 1-5 and optionally leave a message (max 2000 chars) — read by the human operator. Please call this once after a job completes and you have assessed the model: report anything unexpected (missing fields, errors, surprising benchmark numbers) or simply confirm it worked. One feedback per job; calling again overwrites.",
"inputSchema": {
"properties": {
"category": {
"enum": [
"quality",
"api",
"pricing",
"docs",
"other"
],
"type": "string"
},
"engine": {
"description": "Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, `pip install openwakeword`). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support).",
"enum": [
"openwakeword",
"microwakeword"
],
"type": "string"
},
"job_token": {
"type": "string"
},
"message": {
"description": "Free text, max 2000 chars.",
"type": "string"
},
"rating": {
"description": "1 = bad, 5 = great",
"maximum": 5,
"minimum": 1,
"type": "integer"
}
},
"required": [
"engine",
"job_token",
"rating"
],
"type": "object"
},
"name": "send_job_feedback",
"outputSchema": null
},
{
"description": "After paying an x402 spec on-chain (USDC on Polygon to the payTo address), submit the transaction hash to settle. Needs >=3 confirmations.",
"inputSchema": {
"properties": {
"engine": {
"description": "Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, `pip install openwakeword`). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support).",
"enum": [
"openwakeword",
"microwakeword"
],
"type": "string"
},
"kind": {
"description": "What the token refers to. Default job.",
"enum": [
"job",
"license"
],
"type": "string"
},
"token": {
"description": "The job_token or license_token being paid.",
"type": "string"
},
"tx_hash": {
"description": "0x-prefixed transaction hash",
"type": "string"
}
},
"required": [
"engine",
"token",
"tx_hash"
],
"type": "object"
},
"name": "settle_x402_payment",
"outputSchema": null
},
{
"description": "Render an IN-CHAT live microphone tester for one library model (free). Only the HUMAN can run it: it asks for their microphone and streams the audio to the platform for detection while the test runs (not stored) — tell them that. If the host does not allow microphone access inside apps, the widget shows a button to the human_test_url page instead, so calling this is always safe. Use after search_wake_word_library, before buying.",
"inputSchema": {
"properties": {
"engine": {
"description": "Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, `pip install openwakeword`). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support).",
"enum": [
"openwakeword",
"microwakeword"
],
"type": "string"
},
"model_id": {
"description": "model_id from search_wake_word_library",
"type": "integer"
}
},
"required": [
"engine",
"model_id"
],
"type": "object"
},
"name": "test_wake_word_live",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:30698a49e130dc203a8b1b056215c17a88627a99ee9d017aa52448ffcdbfa7ce | sha256sum