Merge or replace dictionary terms for TypeWhisper speech recognition. Add or update terms with optional similarity settings to customize transcription output.
GPL 3.0
467,133 tools. Updated 2026-08-20 19:04
"Speech recognition technology and systems" matching MCP tools:
- Lists all installed Speech-to-Text engines to identify available voice recognition options.MIT
- Generate subtitles from audio using AI speech recognition in DaVinci Resolve Studio. Configure language, preset, character count, line breaks, and gap.MIT
- Retrieve a list of available speech recognition and synthesis models and voices to select the right options for transcription or voice generation.MIT
- Retrieve the subtitle (content) from a TikTok video URL. Supports video URL or ID, and optional language code to get subtitles in a specific language; defaults to automatic speech recognition.MIT
- Assess EU AI Act compliance, prohibited uses, and bias risks for biometric AI systems, including facial recognition, emotion detection, and behavioral biometrics.MIT
Matching MCP Servers
- AlicenseAqualityDmaintenanceMCP server integrating VolcEngine for automatic speech recognition (ASR) and text-to-speech (TTS), converting audio to text or text to audio files.22MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides text-to-speech capabilities using the Kokoro TTS model, offering multiple voice options and customizable speech parameters.4311MIT
Matching MCP Connectors
Hosted speech-to-text + speech emotion/tone analysis for agents. No install; trial keys built in.
Pronunciation scoring, speech-to-text, and text-to-speech for language learning
- Retrieve the processing status and outcome of an async speech recognition job by providing its task ID.MIT
- Retrieve subtitles or content for any TikTok video URL. Optionally specify language code; defaults to automatic speech recognition.MIT
- Transcribes audio to text using speech recognition. Accepts Base64 encoded audio and returns the spoken content as text.MIT
- Retrieve visitor device and technology breakdowns: device types, brands, browsers, versions, OS, and screen resolutions. Use this data to segment audience and optimize experiences.MIT
- Convert spoken audio to text with automatic speech recognition. Use a URL or file path to generate written transcripts.MIT
- Generate speech for meeting bots using text-to-speech technology to vocalize text during video calls with customizable voice options.MIT
- Convert text into speech with customizable voice, rate, volume, and pitch settings using Microsoft Edge's text-to-speech technology.MIT
- Converts Base64-encoded audio to text using Yandex SpeechKit speech recognition. Supports multiple languages and audio formats.MIT
- Transcribe speech from video files into text using Whisper's automatic speech recognition.Apache 2.0
- Convert text into speech via text-to-speech technology and mark delivered utterances as responded for efficient voice-based communication.
- Convert audio from selected clips into captions using macOS speech recognition to add subtitles automatically.
- Search for Uyuni systems by partial hostname to retrieve matching system names and IDs.Apache 2.0
- Retrieve available voice profiles for text-to-speech and speech-to-speech operations in supported languages.MIT
- Create custom voice profiles from audio samples for text-to-speech and speech-to-speech applications. Analyze MP3 or WAV files to generate voice replicas that mimic original audio characteristics.MIT