Re-sync lips in an existing talking video to new spoken words. Dub a short clip by providing text for TTS or an audio track to match.
MIT
306,308 tools. Last updated 2026-07-25 06:30
"A platform providing TTS (Text-to-Speech) capabilities" matching MCP tools:
- Convert text to speech audio and save it to a file using Smallest AI's Lightning TTS. Supports multiple languages, voices, and output formats.MIT
- Retrieve available voice profiles for text-to-speech and speech-to-speech operations in supported languages.MIT
- Generate spoken audio from text using Edge TTS. Choose voice, speaking rate, and pitch. Outputs audio file path.MIT
- Uses text-to-speech to read text aloud on the host computer, with optional voice selection and Windows volume control.MIT
- Clone a voice from a reference audio sample and its transcript to synthesize speech. Provide the text to speak in that cloned voice.MIT
Matching MCP Servers
- Alicense-qualityAmaintenanceText-to-speech MCP server that enables AI assistants to read text aloud on the user's computer using Windows SAPI, with no API key or cloud service required.Last updatedMIT
- Flicense-qualityDmaintenanceAn MCP server that provides speech-to-text transcription and speaker diarization using OpenAI Whisper and pyannote.audio.Last updated
Matching MCP Connectors
Hosted pay-per-use TTS: 54 neural voices, 9 languages incl. Brazilian Portuguese. $10 free credits.
Pronunciation scoring, speech-to-text, and text-to-speech for language learning
- Converts text to natural speech via Deepgram Aura. Returns a downloadable MP3 URL.MIT
- Generate natural-sounding speech from text. Choose from multiple models and customize voice, speed, and style.MIT
- List the text-to-speech voice presets available for generating voice messages in email and SMS sent by AI agents.MIT
- Convert text to speech with cloned voices and emotion tags. Supports wallet authentication without a Venice account.MIT
- Convert text to speech and deliver it as a voice call to one or more phone numbers. Send automated voice messages directly to recipients.MIT
- Generate speech from text with a specified voice, language, and emotional tone. Returns an audio URL for immediate use.MIT
- Convert text to speech into OGG/Opus audio files that play as native Telegram voice notes when attached, using configurable TTS backends including local Kokoro or OpenAI options.MIT
- Retrieve a list of over 50 text-to-speech voices spanning multiple languages, including Chinese and English, for use in TTS synthesis.MIT
- Convert text to speech and save audio to a file. Customize voice, model, and output format for realistic speech synthesis.MIT
- Generate spoken audio from text using TTS synthesis. Supports multiple voices and audio formats for voiceovers, narrations, and podcasts.MIT
- Speak a short text message using configured TTS provider, queued to avoid overlap. Falls back to system TTS for reliability.MIT
- List available AI compute models with pricing and capabilities. Grouped by type: text, image, video, TTS, STT, embeddings. Free — no payment required.MIT
- Convert text into speech audio and add it to a DaVinci Resolve timeline at a specified timecode using AI speech generation.MIT
- Converts text to speech and plays it aloud. Uses a neural TTS server if configured, otherwise falls back to the system TTS engine.MIT