"Speech & Transcription" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Generate AI images, video, speech, music and presentations from Claude, ChatGPT and Cursor.
Reeltopus is an AI video clipper you can run from Claude, ChatGPT and Cursor. Give it a long video (podcast, stream, webinar, lecture, interview) and it finds the complete moments with a hook and a payoff, ranks them best first and says why each one should work. What the AI does: - AI clip selection with titles, hooks and a reason for every pick - Accurate animated captions in 109 languages, including mixed speech like Hinglish; caption translation into 43 languages - AI Reframe to 9:16, 1:1 or 16:9: tracks the speaker, keeps wide shots and slides whole, stacks screen shares, splits two people far apart - Silence and filler-word removal, swear-word masking, edit by transcript or in plain words - AI B-roll from licensed stock footage, brand kits and templates - Whole-video mode: cut a full podcast into a captioned series - Packaging Lab: test hooks, titles and covers per platform - Thumbnail and Shorts cover generator, LinkedIn PDF carousels - Smart links that count clicks, leads and sales, and post analytics Through this MCP server (43 tools, 4 prompts) an assistant can upload or find your videos, show the clips as playable cards, edit and export them (MP4 up to 4K, SRT/VTT/ASS captions, Premiere, DaVinci Resolve and Final Cut timelines), and post or schedule to YouTube and LinkedIn after you confirm. One prompt, clip_and_schedule, takes your latest video to a scheduled post. OAuth sign-in or an API key. Free plan, no card. Docs: https://reeltopus.com/docs/api/mcp
Speech denoise, transcripts (SRT/VTT), embeddings, reranking, entities and translation.
Your AI assistant's creative studio. Make images, video, music and speech with Kling 4.0, Seedance 2.5, Nano Banana Pro, GPT Image 2.5 and more, billed at real model cost. A second brain learns from every generation and 100+ tested workflows, so results get better the more you make
Turn text into speech with Nigerian and African-accented voices.
Public, read-only search and cited passages from The Old Ways historical-text and mythology reference library. Covers Norse, Greek/Hellenic, Egyptian/Kemetic, Celtic and Zoroastrian traditions. No account or API key required. Imported editions may contain transcription errors; editorial summaries are reading aids rather than passage-level verification. Connection and source policy: https://theoldways.co/ai
Connects an AI assistant to your Lingard account (lingard.app), an app for learning languages with books, news and flashcards. Create topic word collections and add complete cards: translation, part of speech, pronunciation, synonyms, example sentences with translations, and images. Fill in missing fields on existing cards, rewrite example translations, and pause or resume collections, books and news in your daily study sessions. Every change can be previewed before it is saved, and saved words appear in the Lingard apps on iOS, Android and the web. Requires a Lingard account; sign-in uses OAuth.
Drive Veltake Studio from any AI agent: create film and ad projects, have the Studio agent build scenes on the canvas, price and start renders, and export edited cuts. Also makes single images, video, speech and music in one call; every paid call runs only at the price it was quoted.
500+ AI models in one account: find and price models, make images, video, speech and text.
Text to speech and transcription for any AI model: MP3 voiceovers, audio and YouTube to text.
Podcast post-production for an AI agent: transcribe a recording, cut fillers and pauses, clean up the voice, add licensed music that ducks under speech, set chapters and export a finished episode.
Text to speech in 149 languages: MP3 links from any assistant. Free without an account.
Generate text, images, videos, speech and transcripts with your Easy-Peasy.AI account.
Brazilian Portuguese audio and video transcription with speaker diarization and SRT/VTT/DOCX export.
x402 pay-per-call agent tools: token safety/honeypot check, speech to text, TTS, translate, OCR, web
Original comic strips of 3 to 6 panels with speech bubbles, from a story and characters you describe, in manga, cartoon, newspaper or graphic novel style.
One API for 100+ AI video, image, music and speech models.
Audio and speech made 11 of 59 named model launches since 6 Jul 2026, from 6 labs. In the.
Instagram tag/user/post search, details, comments/replies, users/posts, video/Reels speech-to-text.
TopFood publishes digital restaurant menus with QR codes. Give it a menu (text, photo transcription, or description) and it creates a live, shareable menu page the restaurant owner can claim for free — no signup required upfront.
TikTok suggestions,user search,post search/details,comments/replies,creators/posts,speech-to-text.
Verbatim transcription of public video/audio URLs to clean text, SRT, and timestamped records.
Pronunciation assessment, phoneme scoring, speaker voice ID, audio transcription, speech synthesis.
Create, inspect, and manage Wubble music, speech, voice, and sound-effect requests through MCP.
