“audio”

Analyze frames, contact sheets, transcripts, audio, and short video through cost-controlled OpenRouter models, generate video through OpenRouter video models…

Use this skill for AI text-to-speech generation.

Use when the user asks to transcribe speech from audio, video, Instagram Reels, TikTok, YouTube, social-media URLs, or local media files.

Talking-head video from image + driving audio: submit tasks via the wrapped generation API and poll for results; requests go through the Giggle gateway.

Base skill: understand any local audio or video file by sending it to Gemini Flash-Lite (native multimodal — transcribes speech, reads on-screen text/slides…

Generate, iterate, deliver, and lifecycle-manage creative assets (image, video, audio clips, music) with Telegram-first reply delivery, working/final storage…

Force-align ground-truth lyric lines to audio using Replicate dashed/whisperx-subtitles-replicate word timestamps as noisy hints, then output aligned JSON and…

Especialista en la generación de activos visuales cinemáticos y coherentes para proyectos de audio.

Transcribe speech (such as .mp3, .wav, .ogg) into text.

从音频文件中提取文字（语音转文字），需要腾讯云 API 凭据。当用户提到音频转文字、语音识别、ASR、音频转字幕时使用。

Assemble an animated character-explainer video ad (any art style — Pixar-style 3D, claymation, anime, paper-cut, felt) (~77s, 9:16) built on an "N types of X"…

Mandatory pre-publish review gate for a UGC video render.

Use this skill for generative video editing, text-to-video, image-referenced video generation, first-frame-to-video, first-and-last-frame transitions, and…

Transcribe audio to text locally via NVIDIA Parakeet TDT 0.6B ONNX — single clip or batch parallel, no API key

Synthesize speech audio via Gemini 3.1 Flash TTS — single clip, batch parallel, voice + style presets

Implement text-to-speech (TTS) capabilities using the z-ai-web-dev-sdk.

Production pipeline for interactive and generative visual art using p5.js.

Text-to-speech conversion using node-edge-tts npm package for generating audio from text.

Transcribe audio files using ElevenLabs Speech-to-Text (Scribe v2).

Intelligent meeting recording and transcription assistant with automated minutes generation, action item extraction, and sentiment analysis.

Transcribe audio via local whisper-cpp server (no API costs).

Text-to-speech via OpenAI Audio Speech API.

Generates a markdown security audit report from audio analysis results

Transcrire les archives audio en fenêtres successives (par défaut 20 minutes) jusqu’à couvrir tout le fichier.