Image, audio, video, speech (TTS), and transcription generation using activity-specific adapters: generateImage() with openaiImage/geminiImage, generateAudio() with geminiAudio/falAudio, generateVideo() with async polling (openaiVideo/geminiVideo/grokVideo/falVideo, per-model typed durations), generateSpeech() with openaiSpeech, generateTranscription() with openaiTranscription. React hooks: useGenerateImage, useGenerateAudio, useGenerateSpeech, useTranscription, useGenerateVideo. TanStack Start server function integration with toServerSentEventsResponse.
$npx -y skills add tanstack/ai --skill media-generationInstalls into the current project.
Run `npx skills use "https://github.com/tanstack/ai" --skill "tanstack/ai/media-generation"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/tanstack/ai" that are relevant to the current task. Run `npx skills add "https://github.com/tanstack/ai"` and select the relevant skills, then follow their instructions.