发现最适合你需求的 AI 技能
Transcribe audio files (WAV/MP3/M4A/FLAC) to timestamped text using SenseVoice-Small + FSMN-VAD. Supports single-file and batch mode with VAD-anchored per-segment timestamps (~15s granularity). Use when the user wants to transcribe speech/audio, run batch transcription on daylog recordings, or re-transcribe specific dates. Replaces the old whisper-transcribe skill.
SenseAudio Voice - 语音合成 (TTS) + 语音识别 (ASR)，支持语言自动切换
Guide for SenseAudio voice selection, plan-level voice entitlement checks, and cloned voice usage constraints in TTS calls. Use this whenever user asks why a voice_id is unavailable, how to use cloned voices, or how to configure pronunciation/dictionary behavior for clone voices.
Build and debug SenseAudio text-to-speech integrations on `/v1/t2a_v2` and `/ws/v1/t2a_v2`, including sync HTTP, SSE stream, WebSocket event sequencing, hex audio decoding, and voice/audio parameter tuning. Use this whenever user requests TTS generation, low-latency streaming speech, voice selection, or TTS error troubleshooting.
Build and troubleshoot SenseAudio speech recognition integrations, including HTTP transcription (`/v1/audio/transcriptions`), realtime WebSocket ASR (`/ws/v1/audio/transcriptions`), audio quality analysis (`/v1/audio/analysis`), and recognition record queries (`/v1/audio/records`). Use this whenever user asks for speech-to-text, diarization, translation, streaming ASR, or ASR model/parameter selection.
Music perception for AI entities — hear BPM, key, structure, genre, mood, and lyrics in any audio file.
Sends international SMS (USMS) via uspeedo platform HTTP API. Use when the user needs to send international SMS, batch SMS, verification/notification/marketing messages, or when integrating with uspeedo SendBatchUSMSMessage API.
|
|
|
Analyze and improve OpenClaw agent skills by tracking usage, checking skill health, scanning code quality, and generating actionable improvement suggestions. Use when evaluating skill reliability, performance, maintainability, or release readiness.
|
