# Volcengine Speech Synthesis MCP for AI Agents AI Agent Connect > Volcengine Speech Synthesis is the TikTok Voice TTS API. It lets you generate natural speech using ByteDance's iconic voice models. You can convert text to speech in multiple languages, use SSML for precise control, and handle long-form content like audiobooks. It is designed for content creators who need viral-ready audio and accessibility teams looking for high-quality speech synthesis. ## Overview - **Category:** industry-titans - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_w3fkAFQ6qN01Upq1pce75bdrQJBDCI1PUIsyEF2C/ai-agent-connect - **Tags:** volcengine, tiktok-voice, tts, speech, text-to-speech, ai-audio ## Description Volcengine Speech Synthesis is the TikTok Voice TTS API. Imagine you're making a video and need that specific, trendy voice people hear all over TikTok. Instead of trying to find a workaround, you can just tell your AI agent to generate the audio directly. This Connector connects your agent to ByteDance's speech synthesis platform, giving you access to those exact voice models. It's not just about one voice, though. You can pull off natural narrations in Chinese, English, and Japanese, or even use specific markup to make the AI pause in just the right spot or put emphasis on a specific word. If you're putting together an audiobook or a long article, it handles those big chunks of text without breaking a sweat. It's a huge jump from robotic text-to-speech to something that actually sounds human. You can find this in the Vinkius catalog to get your agent set up in minutes, moving from a text prompt to a high-quality audio file without any manual exporting or switching tabs. It removes the friction of navigating complex dashboards or dealing with character limits on standard tools. You just provide the text and the desired vibe, and the Connector handles the rest, delivering professional audio that fits your content perfectly. It offers a range of styles including news, child, and trendy voices, making it versatile for different types of media. You can also adjust the speed and volume to ensure the final product sounds exactly how you envisioned it. ## Tools ### get_audio_formats See which file types like MP3 or WAV are supported for your project. This helps you pick the right format for web streaming or local editing. ### list_voices Browse all available voice models including the popular TikTok styles. Use this to find the perfect match for your specific content. ### synthesize_long_text Convert long articles or documents into speech when the text exceeds standard limits. This is the best way to handle entire chapters or long reports. ### synthesize_ssml Turn SSML tags into speech to control pauses and emphasis. This creates a much more natural flow for serious narration or storytelling. ### synthesize_speech Convert text into multi-language speech with custom speed and volume settings. Use this to create viral voiceovers or accessible content. ## Prompt Examples **Prompt:** ``` Make a TikTok style voiceover for this script: 'Hey guys, check out this new hack!' ``` **Response:** ``` 🔊 Speech synthesized successfully! Using BV033_streaming (TikTok Trendy Female). Audio generated in MP3 format at 24kHz. ``` **Prompt:** ``` List the English voices available for a news style narration. ``` **Response:** ``` 🎙️ Available English voices: - **BV113** (English Female) - **BV115** (English Male) You can also request specific styles like 'News' or 'Trendy' when generating speech. ``` **Prompt:** ``` Convert this 2,000-word article into a natural-sounding audio file. ``` **Response:** ``` 📖 Long-text synthesis started! Your article has been split into 5 chunks for processing. Using a natural narration voice. Processing will take about 45 seconds for the full audio file. ``` ## Capabilities ### Generate TikTok voices Your agent creates audio using the specific viral voice models from ByteDance. ### Handle long-form text The Connector processes entire articles or chapters that exceed standard character limits. ### Apply SSML markup You get precise control over pauses, emphasis, and intonation for more natural speech. ### Synthesize multi-language speech The agent produces natural audio in Chinese, English, Japanese, and other supported languages. ### Select audio formats You can choose between MP3, WAV, OGG Opus, or PCM based on your specific project needs. ### List available voices Your agent can browse all available models to find the right style for your project. ## Use Cases ### Viral TikToks A creator asks their agent to make a trendy voiceover for a script, and the agent generates the audio using the TikTok female voice. ### Audiobook Production A producer feeds a 5,000-word chapter to the agent, which uses synthesize_long_text to create a full narration. ### App Accessibility An engineer tells the agent to add speech to a button, and the agent generates a high-quality voice file for a web app. ### Multi-lingual Ads A marketing lead asks for a Japanese version of a slogan, and the agent synthesizes the speech in the correct language. ## Benefits - Get the exact TikTok voices people recognize by using synthesize_speech to create viral-ready audio. - Handle entire books or long articles without manual splitting thanks to synthesize_long_text. - Fine-tune every pause and emphasis using synthesize_ssml for a more human, less robotic delivery. - Support for multiple languages like Chinese and Japanese means you can reach a global audience with one tool. - Choose your preferred output via get_audio_formats to match your specific web or editing requirements. ## How It Works The bottom line is you get high-quality ByteDance speech synthesis directly within your AI chat. 1. Subscribe to the Connector and provide your Volcengine Access Key and Secret Key 2. Choose your desired voice style or language through your AI client 3. Receive a direct audio URL or data file ready for use ## Frequently Asked Questions **Does Volcengine Speech Synthesis have the TikTok voices?** Yes, it includes the specific voice models used for viral TikTok effects, allowing you to create that recognizable trendy sound for your videos. **Can I use this for long audiobooks?** Yes, it has a specific tool for long-form text that allows you to convert articles and chapters exceeding 1,024 characters into narration. **Does it support multiple languages?** Yes, it supports synthesis in Chinese, English, and Japanese, making it great for multi-lingual content creation. **How do I make the voice sound more human?** You can use SSML tags to control pauses, emphasis, and intonation, which makes the speech sound much more natural and less like a robot. **What audio formats can I get?** You can choose from several formats including MP3 for web use, WAV for editing, and OGG Opus for efficient streaming. **Is Volcengine Speech Synthesis good for commercial use?** Yes, it is a professional-grade platform used by creators and developers for high-quality narration, accessibility, and content production. **What makes Volcengine TTS different from other TTS services?** Volcengine powers the iconic TikTok TTS effects used in billions of videos. It offers industry-leading Chinese speech quality, trendy social media voices, and ByteDance's proprietary neural voice technology. **Which languages are supported?** Chinese (Mandarin), English, Japanese, and more. Use language parameter: 'zh' for Chinese, 'en' for English, 'ja' for Japanese. Each language has multiple voice styles. **What's the max text length?** Standard synthesis supports up to 1024 characters per request. For longer texts, use the synthesize_long_text tool which automatically handles chunking and combining results for articles and audiobooks.