Voice & voiceover: agent skills for AI voiceover and text to speech

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page.

Text to speech, voiceover, voice cloning, dialogue and dubbing. 37 skills for Claude Code, Codex and Grok, by type: workflows take a brief to a finished video, effects and styles change how it looks, prompts and guides teach the agent the craft, models run the generation.

How-to tutorials

• How to add voiceover and music to a video with AI: A professional voiceover and a fitting music bed added to your video or screen recording.

Skills (37)

Prompts (2)

• Replicate Prompt Videos — Replicate: Prompt video models like a director: shots, camera motion, four audio layers, dialogue, time-coded beats.
• FLUX 3 Audio & Dialogue — Black Forest Labs: Direct FLUX 3's generated sound: dialogue, voiceover, ambience, effects, music, silence and timing.

Effects (4)

• J-Cut — varg: Shot B's sound starts before its picture. The ear arrives first and pulls the viewer into the next scene.
• L-Cut — varg: Shot A's sound keeps playing after the picture cuts to B. Carries a line or a mood across the edit.
• Sound Match Cut — varg: Two different sounds that rhyme (a scream and a train whistle) bridge the cut and link the two scenes.
• Audio Crossfades, J and L in FFmpeg — varg: Crossfade audio with acrossfade, or build J/L-cuts by delaying one track with adelay and mixing with amix.

Guides (1)

• HyperFrames Media Use — HeyGen: Find or make every asset a video needs: music, SFX, voiceover, images, logos, avatars, transcripts, grades.

Workflows (2)

• AI Podcast Creation — inference.sh: Produce audio podcasts and audiobooks with multi-voice TTS, music beds, intros, outros and ffmpeg.
• Bitwize Music (Suno Album Studio) — bitwize-music-studio: A 53-skill Claude Code plugin for human + AI albums on Suno: lyrics, style prompts, stem mixing, mastering, release.

Models & tools (28)

• varg AI — varg: The official varg skill: videos, images, speech and music through one API key, rendered in the cloud or locally.
• Higgsfield Generate — Higgsfield: Generate images, video, 3D and audio across 30+ models, plus ad videos and virality scoring, from one CLI.
• fal Models Catalog — fal: Choose the right fal endpoint for any modality from curated picks: image, video, 3D, audio and vision.
• ElevenLabs Dubbing — ElevenLabs: Dub video and audio into other languages while keeping each original speaker's voice.
• ElevenLabs Music — ElevenLabs: Compose songs, instrumentals, jingles and background tracks from a prompt or a section-by-section plan.
• ElevenLabs Sound Effects — ElevenLabs: Generate sound effects and ambiences from a text description, including seamless loops.
• ElevenLabs Speech to Text — ElevenLabs: Transcribe audio and video with word timestamps, speaker labels and keyterms, ready for subtitles.
• ElevenLabs Text to Speech — ElevenLabs: Turn scripts into natural voiceover in 90+ languages with ElevenLabs voices, streaming and stitching.
• ElevenLabs Voice Changer — ElevenLabs: Re-voice a recording in a different voice while keeping its emotion, timing and delivery.
• ElevenLabs Voice Isolator — ElevenLabs: Strip background noise and music from dialogue to get clean, isolated speech.
• Gemini API Dev — Google Gemini: Write current Gemini API code, including Nano Banana image generation, Omni video and Gemini TTS.
• AI Voice Cloning — inference.sh: Generate expressive voices in 100+ languages with Inworld TTS-2, ElevenLabs and more, from one CLI.
• Dialogue Audio — inference.sh: Produce multi-speaker dialogue audio with speaker tags, emotion and pacing for podcasts and explainers.
• ElevenLabs Dialogue — inference.sh: Generate a whole multi-voice conversation as one audio file with ElevenLabs, from a script.
• ElevenLabs Dubbing (inference.sh) — inference.sh: Dub audio or video into 29 languages while keeping the speaker's voice, via inference.sh.
• ElevenLabs Sound Effects (inference.sh) — inference.sh: Generate royalty-free sound effects from text with ElevenLabs, via inference.sh.
• ElevenLabs TTS (inference.sh) — inference.sh: Voice scripts with ElevenLabs v4, v4 Turbo, v3, Multilingual v2 and Flash, via inference.sh.
• ElevenLabs Voice Changer (inference.sh) — inference.sh: Re-voice a recording into another voice while keeping words and emotion, via inference.sh.
• ElevenLabs Voice Isolator (inference.sh) — inference.sh: Remove background noise and isolate vocals from any recording with ElevenLabs, via inference.sh.
• Text to Speech — inference.sh: Voice any script with Inworld TTS-2, ElevenLabs, Dia, Kokoro or Chatterbox from one CLI.
• inference.sh CLI — inference.sh: Log in to inference.sh and run its catalog of AI apps — image, video, audio, LLMs, search — from one CLI.
• Runway Dev — Runway: Build Runway's image, video and audio models into your app: live API contracts, SDK and server-side keys.
• Runway Dev Models — Runway: Add a direct Runway model endpoint to your app for image, video or audio, following the live contract.
• Runway Media — Runway: Generate and edit images, video, music, speech and sound effects from chat with Runway's MCP tools.
• Runway Studio Skills — Runway: Run Runway's API from Python scripts: text, image and video-to-video, character performance, images, TTS.
• Video Translator — papawaigo, beta: Translates and dubs a video into Chinese or English and returns a preview link
• dLazy Kling TTS — dlazyai, beta: Kling text-to-speech in Chinese or English with 60+ preset voices, via dLazy
• dLazy Kling Voice Clone — dlazyai, beta: Clones a voice from a reference audio file with Kling, via the dLazy CLI