speech
673 MCP servers tagged speech, 121 up right now. Live servers first, then by uptime; never by payment.
- com.scriptivox.www/transcription needs login 0 agent searches in 30 days
Transcribes audio and video in 119 languages and manages a library of resulting transcripts.
- com.sfxengine/sfx-engine needs login 0 agent searches in 30 days
Generates sound effects and music from text prompts and returns URLs to the resulting audio files.
- com.siftclips/sift-clips needs login 0 agent searches in 30 days
Lets an agent search shared video footage by on-screen content, spoken words, or people appearing in it.
- com.spoolfield/spoolfield needs login 0 agent searches in 30 days
Creates short vertical videos with word-by-word captions, generates transcripts, and converts files from a video link.
- com.sunoboard/sunoboard needs login 0 agent searches in 30 days
Generates AI music and sound effects for games and videos using multiple audio model providers.
- com.tidewellsoftware/media-transcriber needs login 0 agent searches in 30 days
Transcribes audio, video and podcast feeds to text using Whisper, letting an agent turn recordings into searchable transcripts.
- com.toughtongueai/mcp needs login 0 agent searches in 30 days
Lets an agent create voice-agent scenarios, retrieve session analytics, place SIP calls, and schedule meeting bots.
- com.transcribevideototext/transcribe needs login 0 agent searches in 30 days
Lets an agent transcribe audio and video files into text in 100+ languages, with speaker labels and webhook delivery of results.
- com.transcript1/mcp needs login 0 agent searches in 30 days
Lets an agent transcribe and translate audio from social media video links or uploaded files.
- com.transcriptmax/transcriptmax needs login 0 agent searches in 30 days
Transcribes YouTube videos with Whisper, then generates summaries and chapters and enables semantic search across the transcript corpus.
- com.useears/ears needs login 0 agent searches in 30 days
Transcribes audio and video from a URL or local file into text and SRT subtitle output.
- com.valossa/video-assistant-mcp needs login 0 agent searches in 30 days
Lets an agent analyze videos, retrieving transcripts, summaries, visual scenes and shots, clips, and answering questions about content.
- com.vidwords/youtube needs login 0 agent searches in 30 days
Fetches YouTube video transcripts, searches spoken content, and reads on-screen frames with timestamp citations.
- com.vocuno/vocuno needs login 0 agent searches in 30 days
Generates songs with vocals, creates covers, separates stems, converts voices, and masters or edits audio tracks.
- com.voxdub/voxdub needs login 0 agent searches in 30 days
Creates dubbing rythmo bands: transcribes uploaded video, edits lines, applies styling, and exports the result.
- com.watchanyvideo/watch-any-video needs login 0 agent searches in 30 days
Lets an agent analyze YouTube videos, answering questions about visual and audio content with timestamps.
- com.wavelocus/assistant needs login 0 agent searches in 30 days
Lets an agent review local voice recording levels and share approved measurements, after OAuth sign-in.
- com.whispermemos/whisper-memos needs login 0 agent searches in 30 days
Lets an agent read, summarize, and act on voice memos recorded through the Whisper Memos app.
- com.whispifys/whispifys needs login 0 agent searches in 30 days
Lets an agent search, read, and query transcripts of Microsoft Teams calls with speaker names attributed.
- com.wixzel/voice needs login 0 agent searches in 30 days
Lets an agent build voice agents and place live outbound phone calls through an MCP client.
- com.wowreveal/wowreveal needs login 0 agent searches in 30 days
Generates narrated vertical short videos from supplied video links, with AI-written story, voiceover, captions, and clips.
- com.zurelay/mcp needs login 0 agent searches in 30 days
Generates images, videos and speech audio using several hosted generative models.
- co.pepys/pepys-mcp needs login 0 agent searches in 30 days
Transcribes audio and video with speaker diarization, exporting timed SRT or VTT subtitles, including batch processing of podcast feeds.
- co.wave/mcp needs login 0 agent searches in 30 days
Lets an agent search and retrieve notes, quotes, and actions from recorded phone calls, meetings, and in-person conversations.
- co.wisprs/wisprs needs login 0 agent searches in 30 days
Transcribes audio, video and YouTube links, and lets agents search, summarize and export the resulting transcripts.
- dev.cotlet/otter needs login 0 agent searches in 30 days
Lets an agent search meeting transcripts and summaries from Otter.ai and export transcript text for review.
- dev.heard/heard needs login 0 agent searches in 30 days
Lets an agent send spoken progress updates to a user's Mac and receive the user's replies back.
- dev.pages.audio-transcription/audio-transcription needs login 0 agent searches in 30 days
Transcribes audio files with Whisper through an Apify actor, returning transcripts and per-file processing status.
- dev.recapp/recapp needs login 0 agent searches in 30 days
Lets agents record narrated product demos and retrieve transcripts, summaries, and searchable recordings.
- dev.secretvoice/mcp needs login 0 agent searches in 30 days
Generates spoken audio from text using selectable voices across many languages, including multi-voice scenes and emotional vocal cues.
- dev.voidless/voidless needs login 0 agent searches in 30 days
Generates game art assets like sprites, animations, tilesets, sound effects, music, and 3D models for developers.
- fr.fonixia/agent-vocal needs login 0 agent searches in 30 days
Lets an agent create, configure and manage an AI phone receptionist (standardiste) via a Fonixia account.
- id.jameela/jameela needs login 0 agent searches in 30 days
Lets an agent fetch Google Meet transcripts, summaries and action items, and dispatch a notetaker bot to meetings.
- io.avatrix/avatrix needs login 0 agent searches in 30 days
Generates AI influencer photos, UGC-style videos and voiceovers that keep a consistent face, connected through OAuth.
- io.blumify/transcripts needs login 0 agent searches in 30 days
Transcribes YouTube videos and podcasts, then lets an agent summarize, query, or translate the transcript content.
- io.callin/callin needs login 0 agent searches in 30 days
Lets an agent manage AI phone voice agents, review call history, and read call transcripts.
- io.callnode/mcp needs login 0 agent searches in 30 days
Lets an agent read call logs and texts, send SMS/MMS messages, and place phone calls from configured numbers.
- io.conversiontools/mcp needs login 0 agent searches in 30 days
Converts files between 140+ formats, runs batch jobs, performs OCR and AI extraction, and handles text-to-speech and speech-to-text.
- io.dadan/dadan needs login 0 agent searches in 30 days
Lets an agent search and share screen recordings, transcribe and translate videos, and retrieve AI meeting notes.
- io.elevenlabs/mcp needs login 0 agent searches in 30 days
Lets an agent manage voice agents and generate speech, music, sound effects, images, and video via ElevenLabs.
- io.github.AceDataCloud/mcp-fish needs login 0 agent searches in 30 days
Lets an agent generate speech audio from text, with voice conditioning, through the Fish Audio API.
- io.github.adamperlis/walkie-mcp needs login 0 agent searches in 30 days
Lets an agent search recorded meetings and read their notes, action items, participants, and transcripts.
- io.github.AgentLineHQ/agentline needs login 0 agent searches in 30 days
Lets an agent place and receive voice calls, send and receive SMS, and manage phone numbers through MCP tool calls.
- io.github.AgentPhone-AI/agentphone needs login 0 agent searches in 30 days
Lets an agent provision a phone number, send and receive text messages, and place or handle voice calls.
- io.github.ai-directories-clients/transclipper needs login 0 agent searches in 30 days
Transcribes short-form and YouTube videos, scores their virality, finds breakout clips, and drafts hook lines.
- io.github.aqua-voice/aqua-voice needs login 0 agent searches in 30 days
Searches stored voice dictations, reads their transcripts, and manages dictionary and settings entries.
- io.github.arcmira/arcmira needs login 0 agent searches in 30 days
Searches YouTube video transcripts for exact quotes, retrieves full transcripts, and identifies speakers.
- io.github.ArpitGandhi1934/yugenox-instagram-reels-transcript needs login 0 agent searches in 30 days
Lets an agent pull spoken-word transcripts from public Instagram reels, along with each reel's caption and engagement stats, without…
- io.github.ArpitGandhi1934/yugenox-instagram-scraper needs login 0 agent searches in 30 days
Lets an agent pull public Instagram reels, posts, profiles and comments, and transcribe reel audio to text, without logging in.
- io.github.Aryan1982/xlaunch needs login 0 agent searches in 30 days
Converts a website URL into a narrated launch video, editable via chat, and exports it as MP4.
Previous · Next (page 6 of 14)
All capabilities · Search instead
- 62071 servers
- Last crawl: 2026-11-11T16:39:06.253Z
- API base:
https://api.lookupd.com - MCP URL:
https://api.lookupd.com/mcp