"Speech & Transcription" matching MCP servers:

Connect AI agents to Wavix's communications platform to send SMS, make and manage voice calls, run 2FA flows, and access speech analytics, phone number management, and SIP infrastructure.

Enables an assistant to classify returned fields, judge the current audience, and route only safe content to public speech while protected values are diverted into a short-lived, profile-bound, one-time private handoff. It also explains each privacy decision and records redacted receipts with honest deletion status, backed by a fail-closed policy engine that never passes protected values to optional model or authorization services.

Enables an assistant to turn noisy speech into three confirmable action candidates, then execute only the user-selected candidate after a one-time nonce is verified through a paired device. It also records consent receipts and supports Alexa+ account linking and card-based interaction.

Enables Claude Code sessions to be driven from WhatsApp, with bidirectional messaging, media and voice-note transcription, per-group personalities, and tool-permission approval via emoji reactions. Access is gated by pairing codes and allowlists, and it runs as a plain stdio MCP server using either a linked-device pairing or the official Cloud API.

Enables AI agents to conduct anti-fraud reconnaissance through trap-lure generation, scam speech recognition, account checks, risk grading, and evidence-pack building, all with human-in-the-loop and non-enforcement boundaries.

Runs a plain stdio MCP server that lets a Claude Code session send and receive chat messages from a linked phone number or official business account, including media, voice-note transcription, chunked long replies, and @-mentions. Inbound messages can wake the session, and gated access through pairing codes, allowlists and group policies lets only trusted contacts reach it, with tool-permission prompts approvable remotely by emoji reaction.