Audio Editing

CLI-driven ElevenLabs voice isolator skill for removing background noise and isolating vocals from audio via inference.sh. Ideal for podcast cleanup, interviews, music vocals, noisy recordings, and audio restoration workflows.

Design and run multi-step AI content pipelines that chain image, video, audio, and text tools together via the inference.sh CLI. Use ai-content-pipeline to automate workflows like: generate an image, animate it to video, add sound or voiceover, and prepare content for YouTube, social media, and marketing campaigns.

Generate AI music and full songs from text prompts using ElevenLabs Music, Diffrythm, and Tencent Song Generation via the inference.sh CLI. Ideal for background tracks, soundtracks, social clips, podcasts, and royalty-free music. Supports fast song generation, instrumentals, and full vocal songs.

Create AI-powered podcasts and voice content from text using Kokoro TTS, DIA TTS, and the inference.sh CLI. Mix multiple voices, add music, and assemble full episodes for podcasts, audiobooks, and audio newsletters.

ai-voice-cloning is an inference.sh-based skill for AI voice generation, text-to-speech, and voice cloning from the CLI. It wraps ElevenLabs, Kokoro TTS, DIA, Chatterbox, Higgs, and VibeVoice models for natural speech, multi-voice narration, and voice transformation for audio and video projects.

Create realistic multi-speaker dialogue audio with Dia TTS and ElevenLabs via the inference.sh CLI. The dialogue-audio skill helps you control speakers, emotion, pacing, and conversation flow for podcasts, audiobooks, explainers, character scenes, and other conversational content.

Generate polished multi-speaker dialogue audio with ElevenLabs via the inference.sh CLI. Turn structured scripts into natural-sounding conversations with multiple voices in a single file for podcasts, audiobooks, explainers, tutorials, character dialogue, and video scripts.

elevenlabs-dubbing lets you automatically dub and translate audio or video into 29 languages using the inference.sh CLI, preserving the original speakers’ voices. Ideal for video editors, podcasters, and localization teams who need fast, high‑quality multilingual versions of existing content.

Generate original AI music from text prompts using the inference.sh CLI and ElevenLabs. Control duration, style, and mood to create royalty-free background music, soundtracks, jingles, podcasts beds, and game audio directly from your terminal.

Generate AI sound effects from text prompts using ElevenLabs via the inference.sh CLI. Ideal for video editors, game developers, podcasters, filmmakers, and content creators who need fast, royalty-free sound design. Supports text-to-sound-effect, adjustable duration, and prompt control for cinematic, ambient, and game-ready SFX.

High-accuracy ElevenLabs speech-to-text via inference.sh CLI using Scribe v1/v2 models. Supports transcription, speaker diarization, audio event tagging, word-level timestamps, forced alignment, and subtitle generation for meetings, podcasts, and other audio workflows.

ElevenLabs text-to-speech via inference.sh CLI, with 22+ premium voices, multilingual support, and fast model options for production voice generation workflows.

ElevenLabs voice changer skill using the inference.sh CLI (infsh) to transform recorded speech into a different synthetic voice while preserving content and emotion. Supports eleven_multilingual_sts_v2 (70+ languages) and eleven_english_sts_v2 for speech-to-speech, accent change, and voice disguise in content creation, dubbing, and character voices.