Guide
Updated 2026-07-26 · XFORGE AI
Audio Studio covers short TTS, voice clone, and talking-head / lipsync video. Costs differ wildly — treat TTS as cheap and InfiniteTalk-class video as premium.
Short TTS is typically 1–2 credits. Voice clone is higher (about 30). Talking-head ~5s starts at 50 credits and rises with duration; HD resolutions can double cost.
Aggregator rates for InfiniteTalk-class models are often ~$0.20 per second (more at 720p). Credits are set so Pro/Agency plans do not lose money when creators run lipsync heavily.
Generate voiceover first (cheap), edit the script, then spend talking-head credits once. Prefer top-up credits ($0.05) for heavy lipsync batches.