Transcribe local audio files to text or subtitle formats (SRT, VTT) with speaker diarization. Supports JSON and verbose output, optional context prompts, and language selection.
MIT
510,032 tools. Updated 2026-09-03 17:32
"How to record desktop audio and transcribe it to a VTT file" matching MCP tools:
- Check if the Diagrammo desktop app is installed on macOS to decide how to deliver diagrams: open the source file in the app when available, otherwise fall back to a shareable online URL.MIT
- Burn styled, karaoke captions into a video using word timestamps from a transcript. Use transcribe output to add social-style captions locally with ffmpeg.Apache 2.0
- Generate word-level timestamped transcripts from audio or video to caption videos, read voiceovers, or analyze competitor ad scripts.Apache 2.0
- Open the Sync upload widget to choose a ChatGPT file or upload a local image/audio, converting it to a durable assetId for later processing.MIT
- Convert text into spoken audio and save it as a file. Choose AI voice, language, speed, and format to generate speech on demand.MIT
Matching MCP Servers
- AlicenseNot gradedqualityBmaintenanceMCP server that routes Claude Desktop chat into Claude Code, enabling headless execution and terminal handoff with session continuity.MIT
- AlicenseNot gradedqualityCmaintenanceA minimal MCP server with get_weather and create_ticket tools, used for testing MCP servers across protocol, unit, eval, transport, and auth layers.MIT
Matching MCP Connectors
Transform any blog post or article URL into ready-to-post social media content for Twitter/X threads, LinkedIn posts, Instagram captions, Facebook posts, and email newsletters. Pay-per-event: $0.07 for all 5 platforms, $0.03 for single platform.
Transcribe audio & video to text for AI agents: 100+ languages, speaker labels, webhooks.
- Transcribe audio to text in 32+ languages via Smallest AI's Pulse STT. Provide a file path or URL and specify language; optional diarization, PII redaction, timestamps, and emotion detection.MIT
- Convert an audio file URL into accurate, punctuated text with timestamps, language detection, and optional speaker labels. Upload up to 15 minutes of audio or split longer recordings for transcription.MIT
- Identify the active connection mode (DESKTOP or CLOUD) and obtain instructions to enable the other mode.MIT
- Transcribe audio files into text with automatic language detection and optional speaker diarization. Save transcripts to file or return them directly to the client.MIT
- Transcribe audio or video into word-timestamped captions for your video project. Runs Whisper locally—no API key or upload required—and accepts a URL or local file path.Apache 2.0
- Convert text to audio with customizable voice, speed, and emotion, saving the file to a specified directory. Integrates with MiniMax API for high-quality speech synthesis.MIT
- Convert any video or audio URL into formatted Markdown notes: downloads, transcribes, and saves to Desktop. Also writes saved note content to a file.MIT
- Transcribe an audio file into text directly from your machine—no upload needed. Supports Arabic and optional speaker labels.MIT
- Convert audio from a public URL into text. Supports mp3, wav, m4a, ogg and other formats.MIT
- Convert subtitles between SRT and VTT, and shift cue timings by milliseconds. Runs locally in your browser—no server needed.MIT
- Transcribe audio from a URL or file path using Deepgram Nova-2. Get transcript, confidence score, word-level timestamps, and a sealed ProofLink receipt for verification.MIT
- Transcribe local audio or video files by providing their absolute path to the TypeWhisper app. Supports language hints, task type selection, engine overrides, and dictionary corrections.GPL 3.0
- Transcribe base64-encoded audio to text. Supports multiple formats (mp3, wav, ogg, webm, flac) up to 10MB and various languages via BCP-47 codes.MIT
- Converts speech in an audio file to a different voice and saves the output file to a directory.MIT