"The most widely used models" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Skavio LLC provides hosted Streamable HTTP MCP for PDF operations, searchable OCR, invoice field extraction, document conversion, image/media processing, transcription and meeting workflows. Company OAuth/PKCE or explicitly issued company credentials and prepaid credits are required. Submit measured jobs with idempotency keys, poll status and retrieve authenticated outputs. Review OCR and invoice data before financial posting. This service is separate from x402 blockchain payment verification. Supported operations, prices and limits follow the live catalog. Website: https://getskavio.com/ Docs: https://getskavio.com/processing/docs/mcp/ Support: support@getskavio.com. Privacy: https://getskavio.com/privacy/ Terms: https://getskavio.com/terms/
AI Voice Production Agent: picks from 30+ TTS models, fixes pronunciation, validates every line.
Dial by Aloha Labs gives an AI agent its own real US or Canadian phone number through one remote MCP server, with no install. Signup is open, and agents can sign themselves up with the sign_up tool. Dial reads incoming verification codes, receives texts, and places AI voice calls with 10 voice personas. Free: $5 credit, no card, OTP codes included. Paid plans start at $15/mo.
500+ AI models in one account: find and price models, make images, video, speech and text.
A spoken voiceover of your own text: the script is paced for listening (pauses, emphasis, emotional cues) in the delivery style you describe, then read by one stock male AI voice and returned as an MP3. No voice cloning.
Turn any video or audio recording into text your AI can read, summarize and search. Say "transcribe my video", drop the file on the private link, and your AI reads the transcript. Free plan, nothing to install.
Remote MCP for three phone actions: call_me calls your verified number for decisions, call_person relays a user-approved message to a specified person, and call_business calls businesses for inquiries or bookings. Results return to the agent. Each user supplies a LifeClaw Bearer API key; outbound calls may use account credits. Setup: https://lifeclaw.agentese.ai/mcp
JooVoice lets your AI assistant make real phone calls for you through MCP. Ask it to book a table or appointment, change a reservation, cancel a subscription, request a refund, or check stock and opening hours. Get the outcome back in your chat, with the call recording and transcript. You choose when calls need your approval. Personal calls, such as birthday wishes or family check-ins, use a recipient consent link. Learn more at https://joovoice.com.
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.
Give your AI assistant a real phone line. Place and end real phone calls with AI voice agents, read call transcripts, run a live two-way interpreter between two people who share no language (31 languages, browser link or phone), create and edit voice agents, and search, buy and bind phone numbers in 21 countries. OAuth 2.1 with PKCE — the model never sees your API key; a read-only scope is available. Pay as you go from $0.10/min, $5 free credit for new accounts.
Use your WhisperAI transcripts in Claude, ChatGPT and other MCP clients. Transcribe a public media URL or upload audio and video, with optional speaker labels and a language choice. Search your library, read transcripts with timestamps, export them as text or SRT and VTT captions, pull an AI summary, and translate, rename or delete recordings. Sign in with your WhisperAI account over OAuth. It works on every plan, the free one included, and uses your plan's normal minutes.
A personalized birthday song with the person's name, lyrics written in the conversation and a sung vocal.
Short intro and outro jingles for podcasts, channels and streams: 30 or 60 seconds, instrumental or with a sung tagline that says the show's name.
Audio and speech made 11 of 59 named model launches since 6 Jul 2026, from 6 labs. In the.
Talk with your agents. A voice call in the browser that your agent can start or join.
24/7 AI-hosted radio (LV+EN). Agents read transcripts and ask the hosts questions answered on air.
Podcast transcripts as clean Markdown with real speaker names — via the Spoken API.
One key, 100+ models: chat with any LLM, generate images and speech. Live model list. Free trial.
Connect the OneStepTranscribe MCP server to your AI assistant and turn audio or video into text without leaving the chat. It is a remote server, so there is nothing to install, no API key, and no account. Just add one URL and ask your assistant to transcribe a file.
Sorani & Kurmanji TTS+STT: Kurdish speech most APIs lack. 885 voices, free tier, no key to browse.
