Doubao Open TTS
Text-to-speech synthesis skill powered by Volcano Engine's Doubao API, enabling AI agents to convert text into natural-sounding speech with 200+ voice options across multiple categories including general, roleplay, video dubbing, audiobook, customer service, and fun accents.
🚀 Transform text into natural-sounding speech with Doubao Open TTS. This skill converts any text to audio using Volcano Engine's advanced synthesis technology, offering 200+ diverse voices across multiple languages and styles. Choose from general, roleplay, audiobook, customer service, and fun accent categories. Customize speech speed and volume to match your needs, with support for MP3, PCM, and WAV formats.
💡 Perfect for AI agents that need voice capabilities—create interactive voice assistants, audiobook narration, video dubbing, customer support bots, or engaging storytelling experiences. Seamlessly integrate natural speech synthesis into your agent workflows with simple configuration and flexible voice selection.
✨ Enjoy professional-quality audio output with multilingual support and emotion-aware voices, enabling your agents to communicate naturally and expressively with users.
Requirements
Volcano Engine API credentials including App ID, Access Token, and Secret Key for TTS service
Required Python packages specified in requirements.txt