Video and media skills

Covers working with media files in Remotion through Mediabunny.

Exports a Remotion video to a file by rendering the composition.

Builds an application around Remotion, such as a video-generating SaaS.

Previews a Remotion video in Remotion Studio while it is being built.

Upgrades Remotion and its related packages to a newer version.

Builds voice AI agents with ElevenLabs, such as voice assistants and customer service bots with tools and workflows.

Dubs audio and video into other languages with the ElevenLabs Dubbing API, keeping the original speakers' voices.

Generates music with the ElevenLabs Music API: instrumental tracks, songs with lyrics, background music and jingles.

Generates sound effects from text descriptions with ElevenLabs: ambient sounds, cinematic impacts and UI sounds.

Transcribes audio and video to text with ElevenLabs Scribe v2, for subtitles and meeting transcripts.

Converts text to speech with ElevenLabs voices in more than 90 languages, for voiceovers and voice apps.

Changes the voice in a recording to a different target voice with ElevenLabs, keeping emotion, timing and delivery.

Removes background noise and isolates speech from audio with the ElevenLabs Voice Isolator API.

Builds consistent character designs with fal's genmedia: reference sheets, expression sheets, outfit variations and character-to-video.

Writes cinematic image and video prompts for genmedia: shot language, camera movement, lighting, lenses and colour grade.

Helps pick the right fal.ai endpoint for a task from a catalogue organised by modality.

Covers prompt writing for specific model families on fal.ai, such as Kling and GPT Image.

Authors and runs multi-step media pipelines on fal.ai, as workflow JSON files or with the genmedia CLI.

Uses the genmedia CLI to search, inspect and run more than 1,200 fal.ai model endpoints.

Plans and produces UGC-style creator ads and social proof videos with genmedia, such as testimonials and product demos.

Integration guide for the BFL FLUX API: endpoints, async polling, rate limits, error handling and webhooks, with Python and TypeScript examples.

Checks a FLUX 3 brief before generation and resolves requirements that are missing or in conflict.

Prompting guide for FLUX image models: text-to-image, image-to-image, structured JSON prompts, typography and multi-reference editing.

Generates audio with the Runway API: text-to-speech, sound effects, voice isolation and dubbing.