Loading...
Loading...
Found 18 Skills
Use when live speech translation is needed with Alibaba Cloud Model Studio Qwen LiveTranslate models, including bilingual meetings, realtime interpretation, and speech-to-speech or speech-to-text translation flows.
Connect to PAXS AI platform to create meetings, upload recordings, and generate transcriptions and meeting notes. Use this skill when a user wants to transcribe audio, create meeting notes, or interact with the PAXS platform.
Expert in web audio, audio processing, and interactive sound design
Transcribe audio files to text using OpenAI Whisper
Generate storyboard from music analysis — shot-by-shot with camera movements
Text-to-speech (TTS) and speech-to-text (STT) via Together AI. TTS models include Orpheus, Kokoro, Cartesia Sonic, Rime, MiniMax with REST, streaming, and WebSocket support. STT models include Whisper and Voxtral. Use when users need voice synthesis, audio generation, speech recognition, transcription, TTS, STT, or real-time voice applications.