Agents Index

Embeddings, Rerank & Speech-to-Text (Tanod)

Online

Speech denoise, transcripts (SRT/VTT), embeddings, reranking, entities and translation.

Visit publisherConnectJSON

What it can do: 19 tools

  • embed_texts read-onlymlpeek: 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 10
  • embed_multimodal read-onlymlpeek: 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 pro
  • rerank_documents read-onlymlpeek: 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
  • text_similarity read-onlymlpeek: 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
  • extract_entities read-onlymlpeek: 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): t
  • classify_zero_shot read-onlymlpeek: 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):
  • text_sentiment read-onlyutilpeek: 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 sha
  • text_keywords read-onlyutilpeek: 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 pun
  • text_summarize read-onlyutilpeek: 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, picke
  • detect_language read-onlyutilpeek: 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)
  • denoise_audiomlpeek: 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 m
  • transcribe_audio read-onlymlpeek: 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
  • transcribe_podcast_episode read-onlymlpeek: 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 pod
  • translate_text read-onlymlpeek: 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
  • check_text_for_prompt_injection read-onlymlpeek: 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
  • extract_json_with_schema read-onlymlpeek: 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`
  • text_to_speechmlpeek: 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 synth
  • translate_speechmlpeek: 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
  • translate_document read-onlypdfpeek: 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)

Connect it

Claude Code
claude mcp add --transport http embeddings-rerank-speech-to-text-tanod https://tanod.dev/mcp/ml
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://tanod.dev/mcp/ml
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "embeddings-rerank-speech-to-text-tanod": {
      "url": "https://tanod.dev/mcp/ml"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "embeddings-rerank-speech-to-text-tanod": {
      "type": "http",
      "url": "https://tanod.dev/mcp/ml"
    }
  }
}

Questions

What does Embeddings, Rerank & Speech-to-Text (Tanod) do?

Speech denoise, transcripts (SRT/VTT), embeddings, reranking, entities and translation. It exposes 19 tools to AI assistants.

What tools does Embeddings, Rerank & Speech-to-Text (Tanod) provide?

19 tools, including embed_texts, embed_multimodal, rerank_documents, text_similarity, extract_entities, classify_zero_shot, text_sentiment, text_keywords, text_summarize, detect_language, denoise_audio, transcribe_audio….

How do I connect Embeddings, Rerank & Speech-to-Text (Tanod) to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://tanod.dev/mcp/ml as a custom connector or MCP server. Copy-paste setup is on this page.

Does Embeddings, Rerank & Speech-to-Text (Tanod) require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Embeddings, Rerank & Speech-to-Text (Tanod) online?

As of 2026-11-19 our probe found it online. It answered 67% of our last 3 checks.

Who publishes Embeddings, Rerank & Speech-to-Text (Tanod)?

tanod.dev. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Audio, Voice & Music