Doubao ASR
Low RiskChinese speech recognition API converting recorded audio to text via ByteDance's Doubao Seed-ASR 2.0 model.
About
Doubao ASR provides high-accuracy speech-to-text transcription for audio files using ByteDance's Doubao Seed-ASR 2.0 model, optimized for Mandarin Chinese and other languages. Built on Volcengine infrastructure, it delivers enterprise-grade audio recognition capabilities. Ideal for developers building transcription, voice documentation, and multilingual audio processing applications. Source: https://clawhub.ai/doubao-asr Version: 0.14.0
Related Skills
AnythingLLM: Open-Source Full-Stack AI Application
Open-source full-stack AI application integrating RAG, AI agents, and no-code builder with multi-model support and vector storage.
OpenClaw Multi-Model Strategy and Optimization Techniques
介绍 OpenClaw 的多模型协作策略、本地部署方案、反向提示和 Vibe Coding 等实用技巧的集合
Simmer: AI-Powered Automated Trading Agent for Prediction Markets
OpenClaw 的 Simmer 技能展示了如何构建具有沙盒训练、心跳机制、推理验证和安全护栏的自动交易 AI agent