Retrieve the complete JSON schema for video generation to understand all configuration options, constraints, and examples before creating valid video configurations.
MIT
538,021 tools. Updated 2026-09-09 01:40
"Tools for speech generation, video translation, and voice conversion" matching MCP tools:
- Generate AI subtitles for a hosted video by providing its video ID. Speech is transcribed into a WebVTT track with automatic language detection or a specified ISO code, and attached to the video when complete.MIT
- Turn a script into a spoken MP3 URL by selecting a voice engine and preset, producing standalone voiceover clips up to 900 characters.MIT
- Convert text to speech with selectable voice and language. Get an mp3 URL for standalone use or as voiceover in video composition.MIT
- Automatically lower background music during speech and restore it in pauses. Accepts audio or video as voice input and returns a mixed output.MIT
- Create or update an AI Target for evaluation simulations. Supports generation models, custom endpoints, and voice agents with templates, tools, and HTTP settings.Apache 2.0
Matching MCP Servers
- AlicenseBqualityDmaintenanceEnables image and video generation using BigModel AI's CogView and CogVideoX models via MCP, supporting batch image generation and various configuration options.6494MIT
- AlicenseNot gradedqualityDmaintenanceEnables text-to-speech conversion using Minimax AI's voice synthesis API with automatic upload to Amazon S3. Supports customizable voice settings including model selection, voice ID, and speech speed control.1MIT
Matching MCP Connectors
Generate images, video & speech with Nano Banana, Veo, Omni and Gemini TTS. Pay as you go.
Decision Layer for AI Agents — 58+ tools, Advisor, MCP. Free key: POST /v1/register {}.
- Retrieve available voice synthesis models with IDs and descriptions for text-to-speech operations in the All Voice Lab MCP Server.MIT
- Convert text to speech audio files using specified voices and models, saving results to your chosen directory for accessibility or content creation.MIT
- Convert audio files to different voices while preserving speech content. Transform MP3 or WAV files using voice IDs with adjustable similarity and optional background noise removal.MIT
- Retrieve available voice profiles for text-to-speech and speech-to-speech operations in supported languages.MIT
- Translate video speech into different languages and generate AI-voiced dubs for accessible multilingual content.MIT
- Turn JSON data into formatted documents by filling Carbone templates. Supports format conversion, translations, currency conversion, and batch generation.Apache 2.0
- 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
- Find specific video segments using semantic search across speech, on-screen text, and visuals. Returns timestamps and metadata for precise moment retrieval.MIT
- Send voice calls to one or many recipients using text-to-speech or an audio URL, with per-second billing per recipient.MIT
- List all available voices, personas, languages, pricing tiers, character limits, and speed/quality controls to plan your speech generation call.MIT
- Swap a finished video's narrator voice while keeping the original performance, lip-sync, and background audio. Provide a video URL and voice preset to receive the served URL.MIT
- Obtain a price quote for video generation before queueing the job. Specify model and optional duration; no authentication required.MIT
- Translate text with AI localization using translation memory, style guides, and brand voice. Specify target language, context, glossary, and formality for accurate results.MIT
- Create a new AI voice agent by configuring the language model, text-to-speech, and speech-to-text settings. Define the system prompt and voice to deploy a custom virtual assistant.MIT
- Create a custom voice clone from an audio/video sample via URL or asset ID, and receive a voice ID to use in text-to-speech requests.MIT