{"id":"dev.tanod/ml","slug":"dev-tanod-ml","title":"Embeddings, Rerank & Speech-to-Text (Tanod)","description":"Speech denoise, transcripts (SRT/VTT), embeddings, reranking, entities and translation.","version":"0.1.3","publisher":{"kind":"domain","id":"tanod.dev","label":"tanod.dev","url":"https://tanod.dev"},"website":"https://tanod.dev","repository":"https://github.com/tanod-labs/tanod-mcp","remotes":[{"type":"streamable-http","url":"https://tanod.dev/mcp/ml"}],"packages":[],"published":"2026-11-09","updated":"2026-11-09","status":"online","auth":"","latency_ms":1674,"checked":"2026-11-19","uptime":67,"checks":3,"tools":[{"name":"embed_texts","title":"mlpeek: embed texts as vectors","description":"mlpeek: Create text embeddings. For images too use embed_multimodal; for pair scores use text_similarity. Returns 384-dimension embeddings of 1-64 texts with bge-small-en-v1.5 (English) or multilingual-e5-small (about 100 languages), normalised by default; `input_type` applies the model's query or passage prefix. Each text is cut at the model's 512-token window (`truncated` says so); over 16,384 t","read_only":true},{"name":"embed_multimodal","title":"mlpeek: embed text and images in one vector space","description":"mlpeek: Create multimodal embeddings: images and text in one vector space. For text only use embed_texts. Returns 768-dim vectors of texts and images (URL or base64) in ONE space (EmbeddingGemma 2), comparable by dot product; `dimensions` 512/256/128, `input_type` text prefix, `image_detail` low/standard/high. At most 16 low, 8 standard or 4 high-detail images (10 MB each, public URLs). Over 4,096","read_only":true},{"name":"rerank_documents","title":"mlpeek: rerank documents against a query","description":"mlpeek: Rerank up to 100 documents against a query. For pair scores use text_similarity. Returns 1-100 documents scored against a query by the ms-marco-MiniLM-L6-v2 cross-encoder (Apache-2.0) and sorted best first: index, rank, score (sigmoid of the logit, a relevance in 0-1) and logit; `top_k` keeps the best k. English model. Each text is cut at the model's 512-token window and the answer says so","read_only":true},{"name":"text_similarity","title":"mlpeek: semantic similarity of text pairs","description":"mlpeek: Score the semantic similarity of one or up to 50 text pairs. To rank documents against a query use rerank_documents. Returns the cosine similarity of the embeddings of each text pair (bge-small-en or multilingual-e5-small): one pair as `a` + `b` (also a top-level `similarity`) or 1-50 `pairs`. Input: `a` + `b`, or `pairs`; each text at most 4,000 characters; optional `model`. Each text is ","read_only":true},{"name":"extract_entities","title":"mlpeek: extract named entities from text","description":"mlpeek: Extract named entities: people, organisations, places, dates, money, ... For fields of your own schema use extract_json_with_schema. Returns named entities in English text with spaCy en_core_web_sm 3.8.0 (MIT): text, label (the 18 OntoNotes types: PERSON, ORG, GPE, LOC, DATE, MONEY, ...) and code-point offsets (end exclusive), plus counts per label; at most 2,000 entities (then `entities_t","read_only":true},{"name":"classify_zero_shot","title":"mlpeek: classify text into your own labels (zero-shot)","description":"mlpeek: Classify a text into 1-10 of your labels. For named entities use extract_entities. Returns scores of 1-10 caller-supplied labels for an English text with the nli-deberta-v3-xsmall NLI cross-encoder (Apache-2.0): single-label scores sum to 1 (softmax over the labels), `multi_label` scores each label on its own; sorted best first. Scores are model confidences, not calibrated probabilities. E","read_only":true},{"name":"text_sentiment","title":"utilpeek: score the sentiment of a text (VADER)","description":"utilpeek: Analyze the sentiment of an English text. For your own labels use classify_zero_shot; for counts use text_stats. Returns VADER sentiment of an English text: compound (-1 to 1), positive / neutral / negative shares and a label (positive at 0.05 or more, negative at -0.05 or less), optionally per sentence. A lexicon heuristic: it misses sarcasm and domain jargon. Typically under 1 s. Price","read_only":true},{"name":"text_keywords","title":"utilpeek: extract keyphrases from a text (RAKE)","description":"utilpeek: Extract the keywords and keyphrases of a text. For raw frequencies use text_frequency; for names and places use extract_entities. Returns the top keyphrases of a text by RAKE (phrases between stop words and punctuation, scored by word degree / frequency), with score and count. Typically under 0.3 s. Price: USD 0.002. Free: 10 utilpeek calls per IP per UTC day. The submitted text is never","read_only":true},{"name":"text_summarize","title":"utilpeek: summarize a text by picking its key sentences","description":"utilpeek: Summarize a text by picking its key sentences. For paper abstracts use paper_digest; for counts use text_stats. Returns an extractive summary: the most central `sentences` (or `ratio` of them) by LexRank, picked verbatim and kept in their original order, with per-sentence scores. It does not paraphrase, shorten or check facts. Typically under 0.5 s. Price: USD 0.003. Free: 10 utilpeek ca","read_only":true},{"name":"detect_language","title":"utilpeek: detect the language of a text","description":"utilpeek: Detect the language of a text. To translate use translate_text. Returns the most likely language (ISO 639-1 and 639-3 code, name, confidence) and 3 alternatives, from an offline ensemble of lingua (Apache-2.0) and langid.py (BSD-2-Clause) over 75 languages; `reliable` is true only with at least 20 letters and confidence 0.6 or more. Short text is often flagged unreliable; text with no le","read_only":true},{"name":"denoise_audio","title":"mlpeek: reduce speech noise","description":"mlpeek: Reduce background noise in speech audio. Returns mono 12 kHz WAV/MP3/Ogg speech audio with steady noise reduced by FFmpeg afftdn (no model weights), duration and filter. Public URL or base64, up to 25 MB and 10 minutes; base64 or output=url. Not voice isolation; music and changing noise may remain, and speech may sound altered. Exact/credits are flat; upto bills started minutes after a 0.2","read_only":false},{"name":"transcribe_audio","title":"mlpeek: speech to text and subtitles (SRT, WebVTT)","description":"mlpeek: Speech to text and subtitles: transcribe audio to text, timed segments, SRT and WebVTT. For a podcast episode use transcribe_podcast_episode; to translate use translate_speech. Returns the transcript of audio of up to 10 min and 25 MB; `translate_to_english` gives English; `speakers` labels each segment's speaker; `chapters` adds titled chapters (start, title, gist). Too long, big or unrea","read_only":true},{"name":"transcribe_podcast_episode","title":"mlpeek: transcribe a podcast episode from its RSS feed, a window of up to 10 minutes","description":"mlpeek: Transcribe a podcast episode from its RSS feed: a window of up to 10 minutes as text, timed segments, SRT. For your own audio use transcribe_audio. Returns a transcript window (up to 10 min from start_s) of a podcast episode picked from its RSS feed. Input: `feed_url`, optional episode selector, `start_s`, `duration_s`, `language`, `translate_to_english`. Step start_s by window.next_start_","read_only":true},{"name":"translate_text","title":"mlpeek: translate text offline (English and 14 languages)","description":"mlpeek: Translate text between English and 14 languages. For a PDF use translate_document; for audio use translate_speech; to only name the language use detect_language. Returns the text translated between English and es, fr, de, pt, it, nl, ru, zh, ja, ko, ar, hi, id or tl (other pairs pivot through English): `text`, `source_lang` (detected when you omit `source`, then `detected` is true), `targe","read_only":true},{"name":"check_text_for_prompt_injection","title":"mlpeek: check text for prompt injection (automated, heuristic)","description":"mlpeek: Check text for prompt injection before an agent acts on it. For hidden Unicode use text_unicode_inspect. Returns a `verdict`, a `score` (0-1; `injection` at 0.9 and above) and `chunks`, the flagged sentences with score and offsets. A small open classifier (DeBERTa-v3), automated and heuristic: it can miss new attacks and flag harmless text. At most 20,000 characters; English-first. Over th","read_only":true},{"name":"extract_json_with_schema","title":"mlpeek: extract structured JSON from text under your JSON Schema (small open model, CPU)","description":"mlpeek: Extract JSON from text that always matches your JSON Schema. For fixed entity types use extract_entities. Returns `data`, JSON extracted from the `text` that always parses and validates against your `json_schema` (decoded under a grammar built from it), plus `model`, `usage` (tokens) and `ms`. A small open model on Tanod's CPU, no model API: values can be wrong or missing, so check what ma","read_only":true},{"name":"text_to_speech","title":"mlpeek: text to speech (6 languages, offline)","description":"mlpeek: Speak text aloud in 41 voices: English, Spanish, French, Hindi, Italian, Portuguese. For audio to text use transcribe_audio. Returns the text spoken as audio. Offline neural TTS (Kokoro-82M); the audio is a synthetic voice. At most 2,000 characters; 41 voices in 6 languages (the voice sets the language: write the text in it). Bad input is a 422, a busy or unavailable model a 503, a synthes","read_only":false},{"name":"translate_speech","title":"mlpeek: speech translation: audio in, translated text and speech out","description":"mlpeek: Translate speech: audio to English or 14 languages, optionally spoken. For a transcript in the spoken language use transcribe_audio. Returns speech translation of an audio file of up to 2 minutes: the language is detected and the speech returned as text in `target` (en, es, fr, de, pt, it, nl, ru, zh, ja, ko, ar, hi, id, tl) with timed `segments`, optionally a `transcript` and, with `speak","read_only":false},{"name":"translate_document","title":"pdfpeek: translate a PDF, digital or scanned, to English or 14 other languages as Markdown","description":"pdfpeek: Translate a PDF document, digital or scanned, to English or 14 languages as Markdown. For plain text use translate_text. Returns each page's text (text layer or OCR) translated offline into `target` (default en) as Markdown with a `<!-- page N -->` marker per page, source language and per-page method; `truncated` past the limits. Languages en, es, fr, de, pt, it, nl, ru, zh, ja, ko, ar, h","read_only":true}],"server_info":{"name":"tanod-ml","title":"Embeddings, Rerank & Speech-to-Text (Tanod)","version":"0.1.3","websiteUrl":"https://tanod.dev"},"category":"audio-voice","tags":["memory","productivity","web-search"],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-10-08","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/dev-tanod-ml/"}