"Speech recognition technology and systems" matching MCP tools:

• transcribeA

  US Company Intelligence for AI Agents (SEC EDGAR, x402)A

  Transcribe the actual audio of a YouTube, TikTok or Instagram video with Whisper large-v3. Not caption scraping: the audio is downloaded and run through speech recognition, so it works on videos with no subtitles, in any language, and on TikTok and Instagram where no caption track exists at all. Extraction runs from a real residential IP, reaching sources that refuse datacenter ranges. Returns full text plus sentence-level timestamps. — $0.020000/call, paid per request via x402 (USDC). Use when asked: "transcribe this youtube video", "get the transcript of this tiktok", "speech to text from a video URL".

  ConnectorNo auth

• mureka_create_speechA

  Mureka MCP Server by useapi.net (third-party)A

  Turn text into spoken audio (not singing): text + voice_id from mureka_list_voices, or a multi-speaker conversation [{ voice_id, text }, ...]; up to 5000 characters. Uses the account's speech minutes. A job (20-90 s): the tool waits up to ~50 s and returns the title, duration and mp3 link, or a jobid for mureka_get_job. For songs use mureka_create_song. POST /speech.

  ConnectorAPI key

• transcription_createA

  HubrisA

  Transcribe a recording to text with a speech recognition model from the Hubris catalogue (Whisper, GPT-4o Transcribe, Deepgram, ElevenLabs Scribe and others). Same as POST /v1/audio/transcriptions with the audio sent as base64. Pass the file content itself, base64-encoded — links to files are not accepted. Every byte of the recording is written out inside this call, so it suits clips of seconds, not minutes; send longer recordings through the HTTP API (POST /v1/audio/transcriptions). Spends money from the account balance: most models are billed per second or minute of audio, some per token. usage.cost_rub is what this call cost.

  ConnectorAPI key

• mureka_get_jobA

  Mureka MCP Server by useapi.net (third-party)A

  Read one song, edit, remix, stems or speech job: its status and, once completed, its result (songs with song_id and mp3 links, stems with wav, mp3 and a stems_id, or the speech mp3); a failed job gives the reason. wait: true waits up to ~50 s; call again while it is still running. Jobs are kept 7 days. mureka_list_jobs shows what is running now. GET /jobs/{jobid}.

  ConnectorAPI key

• code_find_usagesA

  searchcodeA

  Find which files in a repository use a given technology, library or framework — with the line number and the import keyword that proves it. Use after code_analyze reports a technology in tech_stack and you need to know which files it is actually in, rather than searching for import statements by hand. Returns file, line, evidence keyword and language. COVERAGE LIMIT: technology detection reads only the first 150 lines of each file, so a file that imports the technology further down, or uses it without a top-of-file import, does not appear. Absence from these results is not proof the file does not use the technology. The count matches the files_using value code_analyze reports for the same technology. Shares the analysis cache with code_analyze — no duplicate work if analyze already ran.

  ConnectorNo auth

• meta_jobs_searchA

  Crawlora MCPB

  Search Meta Careers open-job result records with optional team/technology, location, role, remote, and keyword filters; filters combine with AND, and no filters returns the open-requisition catalog. `q` matches team, technology, location, or req codes—not job titles/descriptions. Use meta_jobs_job for one posting or meta_jobs_list for list discovery.

  ConnectorNo auth

• search_resourcesA

  TangentA

  Ranked search over Tangent's catalogue of design and design-engineering resources (sites, products, component libraries, tools, articles). Use it when you know roughly what you want; narrow with vertical, category, technology, type, pricing or open_source, and page with cursor. For a whole brief, use find_inspiration. Example: {"query": "command menu", "technology": "react", "limit": 5}

  ConnectorNo auth

• lab_wortzeitenA

  FilmLabA

  Every spoken word with its start and end time, for a clip (video_id), an audio track (audio_id) or an uploaded file (project_id + asset_key). Use it to cut pauses without cutting into a word, to time captions, or to land a graphic on an exact word — instead of guessing seconds from the waveform. Up to 20 min of sound per source; the first call transcribes (Fish Audio, about 0.36 USD per audio hour, booked to the operator, not your credits), every later call for the same sound is served from the cache for free. Returns at most 300 s of words per page; continue with `weiter_von_s`. Speech recognition spells names the way they sound — check names before you put them on screen.

  ConnectorOAuth

• meta_jobs_searchA

  Crawlora MCPB

  Search Meta Careers open-job result records with optional team/technology, location, role, remote, and keyword filters; filters combine with AND, and no filters returns the open-requisition catalog. `q` matches team, technology, location, or req codes—not job titles/descriptions. Use meta_jobs_job for one posting or meta_jobs_list for list discovery.

  ConnectorNo auth

• speech_createA

  HubrisA

  Read text aloud with a text-to-speech model from the Hubris catalogue and get the audio file back as audio content. Same as POST /v1/audio/speech. Many models need a voice: the list of voices is on the model card (models_get_pricing → supportedVoices) — pick one from there. The answer is mp3 unless you ask for pcm. Up to 5 000 characters per call, a few minutes of speech; split longer texts or use the HTTP API (POST /v1/audio/speech). Spends money from the account balance: priced per character of text or per second of audio, depending on the model — models_get_pricing shows which. The charge shows up in usage_get.

  ConnectorAPI key

• add_vocabA

  voicehookA

  Teach the call's speech recognition words it keeps mishearing (product names, people, jargon). Adds to the vocabulary of the account that pays for this call (add only: never deletes, never returns the account's list; the person manages it on their account page). terms: words to recognize; fixes: {wrong, right} = a known mishearing and the correct word (right is added to the terms too). Max 20 entries per call of this tool, 100 per call, 50 characters each. Corrections apply right away, the word list from the next sentence or the next call. 409: guest call without an account. Returns added {terms, fixes}, total, call_left, reloaded.

  ConnectorNo auth

• discover_site_avoidanceA

  Jean by Melad LabsA

  Sweep a set of sequences against every exact recognition site in the NEB catalogue and report the sites each one carries far less (avoided) or far more (enriched) often than a stated null predicts, with the false discovery rate controlled across every (sequence, site) test. Avoidance is evidence of the restriction–modification systems a lineage has lived with, and a site a design can rely on being rare. Three nulls: base composition (order-0, Poisson); k-let-preserving shuffles (uShuffle), which holds dinucleotide skews such as CpG depletion in the null rather than reporting them as findings; and R'MES's maximal-order Markov model, the standard in published avoidance analyses, which judges a site of length k against the record's own (k−1)-mers so only what those cannot explain is reported.

  ConnectorNo auth

• discover_site_avoidanceA

  jean — Molecular Biology & GenomicsB

  Sweep a set of sequences against every exact recognition site in the NEB catalogue and report the sites each one carries far less (avoided) or far more (enriched) often than a stated null predicts, with the false discovery rate controlled across every (sequence, site) test. Avoidance is evidence of the restriction–modification systems a lineage has lived with, and a site a design can rely on being rare. Three nulls: base composition (order-0, Poisson); k-let-preserving shuffles (uShuffle), which holds dinucleotide skews such as CpG depletion in the null rather than reporting them as findings; and R'MES's maximal-order Markov model, the standard in published avoidance analyses, which judges a site of length k against the record's own (k−1)-mers so only what those cannot explain is reported.

  ConnectorNo auth

• list_26_systemsA

  mythsensus-mcpA

  Return the canonical list of 26 ancient divination systems Mythsensus implements (slug, English + Thai name, region, required inputs). Use first when asked "what systems do you support?".

  ConnectorNo auth

• propose_contextA

  Forge EngineA

  Propose a new/updated Idea note → Inbox. Title-match to update; send the COMPLETE revised text. Set resync:true ONLY when you rewrote the note FROM the current systems (get_stale lists notes the systems have moved past) — it stops the adopted note from immediately nagging to re-generate the systems it was just written from.

  ConnectorNo auth

• compareA

  askA

  Compare two developmental topics, conditions, or skills side by side (e.g. 'speech delay' vs 'autism'; 'speech therapy' vs 'occupational therapy'). Returns corpus-grounded points of similarity and difference. Non-diagnostic.

  ConnectorNo auth

• transcribe_audioA

  Poly-Glot AI WorkspaceA

  Convert audio to transcript text for Poly-Glot workflows. Use for supplied speech recordings, not for translating text. Provide exactly one source: a publicly reachable HTTPS audioUrl or base64-encoded audioBase64 (without a data-URL prefix). For base64 audio, supply mimeType and filename when known; languageHint can improve recognition. Set detectLanguage=true to identify the resulting text's language. Requires an active trial or Pro. Returns JSON containing transcript text, optional detectedLanguage, provider, and model. Audio is submitted to a transcription provider; do not send material without permission.

  ConnectorNo auth

• hubvibe_speech_transcribeA

  HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, KYC Screening, Stocks, Crypto, NewsA

  Speech to text / audio transcription: transcribe up to 60 seconds or 10 MB of audio with Google Cloud Speech-to-Text and get the transcript with its confidence and detected language. Use it for voice notes, call snippets and clips. Input: audio_base64; optional language_code. Longer audio is refused before payment. $0.25 per call. Returns: transcript, language_code, confidence, model.

  ConnectorNo auth

• ttsA

  SuprsonicA

  Convert text to speech audio. Returns the speech as base64 MP3 audio with its sample rate and the voice used. Use for spoken voice or narration, up to 2,000 characters a call. For sound effects or music use sound-generate. Cost: 2 credits, charged only when a call succeeds.

  ConnectorNo auth

• change_voiceA

  UnsoraA

  Re-voice existing speech into one of the user's cloned voices (Voice Changer, speech-to-speech): keeps the timing and delivery of the source, swaps the voice. The source can be audio or video, up to 5 minutes. Costs about 10 credits per minute. voiceId must be a cloned voice id from list_voices (create one with create_voice_clone). Poll with wait_for_voiceover. Renders a live audio player in app-capable hosts.

  ConnectorOAuth

• search_modelsA

  RelayA

  Lists Relay models by tag and/or text. Common tags: text-to-image, image-to-image, text-to-video, image-to-video, video-to-video, text-to-speech, speech-to-text, text-to-text, text-to-embedding. Returns name, tag and route per model (at most 50). Then call get_model with a name for its input schema.

  ConnectorOAuth