Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
Speech denoise, transcripts (SRT/VTT), embeddings, reranking, entities and translation.
Remote server: your requests and data go to tanod.dev. Claude Code: claude mcp add --transport http embeddings-rerank-speech-to-text-tanod https://tanod.dev/mcp/ml · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
embed_texts — mlpeek: Create text embeddings. For images too use embed_multimodal; for pair scores use text_similarity. Returns 384-dimension embeddings oembed_multimodal — mlpeek: Create multimodal embeddings: images and text in one vector space. For text only use embed_texts. Returns 768-dim vectors of texts arerank_documents — mlpeek: Rerank up to 100 documents against a query. For pair scores use text_similarity. Returns 1-100 documents scored against a query by ttext_similarity — mlpeek: Score the semantic similarity of one or up to 50 text pairs. To rank documents against a query use rerank_documents. Returns the cosextract_entities — mlpeek: Extract named entities: people, organisations, places, dates, money, ... For fields of your own schema use extract_json_with_schema.classify_zero_shot — mlpeek: Classify a text into 1-10 of your labels. For named entities use extract_entities. Returns scores of 1-10 caller-supplied labels fortext_sentiment — utilpeek: Analyze the sentiment of an English text. For your own labels use classify_zero_shot; for counts use text_stats. Returns VADER sentext_keywords — utilpeek: Extract the keywords and keyphrases of a text. For raw frequencies use text_frequency; for names and places use extract_entities. text_summarize — utilpeek: Summarize a text by picking its key sentences. For paper abstracts use paper_digest; for counts use text_stats. Returns an extractdetect_language — 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, denoise_audio — mlpeek: Reduce background noise in speech audio. Returns mono 12 kHz WAV/MP3/Ogg speech audio with steady noise reduced by FFmpeg afftdn (notranscribe_audio — mlpeek: Speech to text and subtitles: transcribe audio to text, timed segments, SRT and WebVTT. For a podcast episode use transcribe_podcasttranscribe_podcast_episode — 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 trtranslate_text — mlpeek: Translate text between English and 14 languages. For a PDF use translate_document; for audio use translate_speech; to only name the check_text_for_prompt_injection — mlpeek: Check text for prompt injection before an agent acts on it. For hidden Unicode use text_unicode_inspect. Returns a `verdict`, a `scoextract_json_with_schema — mlpeek: Extract JSON from text that always matches your JSON Schema. For fixed entity types use extract_entities. Returns `data`, JSON extratext_to_speech — mlpeek: Speak text aloud in 41 voices: English, Spanish, French, Hindi, Italian, Portuguese. For audio to text use transcribe_audio. Returnstranslate_speech — mlpeek: Translate speech: audio to English or 14 languages, optionally spoken. For a transcript in the spoken language use transcribe_audio.translate_document — pdfpeek: Translate a PDF document, digital or scanned, to English or 14 languages as Markdown. For plain text use translate_text. Returns eaNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.