Check Paxa model availability, limits, credit pricing, and supported translation languages before running large speech, transcription, OCR, or extraction jobs.
MIT
750,862 tools. Updated 2026-11-06 11:15
"Speech & Transcription" matching MCP tools:
- Check local speech-to-text backends and media tools, and get install instructions for any missing. Run before transcription to surface missing dependencies as clear answers.Apache 2.0
- Find AI Gateway models this server can call by type (text, image, video, speech, transcription) or search query; returns id, capabilities and price per model.MIT
- Look up English words to get definitions, phonetic transcription, audio pronunciation, synonyms, antonyms, and example sentences. Supports multiple parts of speech for writing agents and NLP preprocessing.MIT
- Queue a YouTube transcription from captions or original audio, choose a language, and verify quoted speech with independent ASR.MIT
- Retrieve video info, a segment storyboard, and a speech timeline in one call, using captions or local transcription and stating which source was used.Apache 2.0
Matching MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP server that provides speech-to-text transcription and speaker diarization using OpenAI Whisper and pyannote.audio.-
- AlicenseAqualityDmaintenanceMCP server for local speech-to-text using Whisper Large V3 (MLX), enabling audio transcription with text/timestamps/SRT output and LLM-based correction, all running offline on Apple Silicon.2MIT
Matching MCP Connectors
Apify actor via Apify's MCP server (Apify token needed): Whisper transcription, per-file status.
Synthesize short texts into WAV audio using offline formant voices in English, German and Spanish
- Convert speech audio to text with automatic language detection for WAV, MP3, WEBM, and OGG files. Provides transcription and identified language.MIT
- Transcribe a clip's audio into text. Provide the clip name to start speech-to-text transcription in DaVinci Resolve.MIT
- Transcribe audio speech to text by sending Base64-encoded audio. Supports multiple languages and various audio formats.MIT
- Rate Telegram voice transcription quality as good or poor to refine speech-to-text accuracy.MIT
- Convert audio and video files to text with automatic speaker detection. Use for meeting minutes, interviews, or any speech-to-text transcription.-
- Starts automatic speech-to-text transcription for the active Premiere Pro sequence (2021+), converting dialogue into editable text for captions and search.MIT
- Rate transcription quality as good or poor to enhance Telegram speech-to-text accuracy.MIT
- Retrieve the most recent voice transcription segments with timestamps, transcript text, confidence scores, and duration to recall just-dictated content.AGPL 3.0
- Search your voice transcription history by entering a query. Find when you mentioned a topic, with results ranked by relevance and including timestamps and transcript snippets.AGPL 3.0
- Retrieve recent voice transcription corrections to analyze systematic Whisper errors, debug mis-transcriptions, or train vocabulary. Returns original and corrected text, confidence delta, timestamp, and correction source.AGPL 3.0
- Speak a quick progress update without waiting for it to finish, letting you keep working while the message plays in the background. Announce completed steps and move on immediately.MIT
- Convert text to speech in a specified voice, returning audio as base64 with duration and token count. Supports format selection, speed adjustment, and continuation for lengthy texts.Apache 2.0
- Wait for an incoming call and answer it for a live phone conversation. Costs money once a call is answered (the call, speech-to-text and text-to-speech are billed).MIT
- Index a video to enable search, visual QA, or full analysis via transcription, captions, and embeddings. Supports uploaded videos or local file paths.Apache 2.0
- Convert audio or video recordings into timed text transcripts in the spoken language, with output options for SRT, VTT, TXT, and JSON.Apache 2.0