[{"data":1,"prerenderedAt":133},["ShallowReactive",2],{"tools-catalog:stepfun":3},{"node":4,"total":11,"items":16,"nodes":86,"pulledAt":132},{"id":5,"displayName":6,"description":7,"shortDescription":8,"url":9,"docsUrl":10,"endpointCount":11,"noMarkup":12,"kind":13,"provider":5,"parents":14},"stepfun","StepFun","Human-like, directable text-to-speech (StepAudio 3) with natural-language delivery control, laughter and breath, six languages, system voices, and instant voice cloning from a 5-10 second recording.","Directable text-to-speech in six languages, with instant voice cloning.","https:\u002F\u002Fplatform.stepfun.ai","https:\u002F\u002Fplatform.stepfun.ai\u002Fdocs\u002Fen",4,"all","provider",[15],"ai",[17,54,67,76],{"provider":5,"providerDisplayName":6,"endpoint":18,"displayName":19,"displayDescription":20,"price":21,"categories":48,"tags":50,"supportedX402Networks":53},"\u002Ftext-to-speech","Text to Speech","Convert text to natural, directable speech (MP3) with a system or cloned voice.",{"type":22,"amount":23,"selectors":26,"variants":31},"PER_UNIT_MATRIX",{"value":24,"currency":25},0.36,"USD",[27],{"label":28,"key":29,"in":30},"Model","model","body",[32,41],{"when":33,"price":35,"label":40},{"model":34},"stepaudio-3-tts",{"type":36,"amount":37,"per":38,"unit":39},"PER_UNIT",{"value":24,"currency":25},10000,"character","StepAudio 3 TTS — per 10,000 characters",{"when":42,"price":44,"label":47},{"model":43},"stepaudio-2.5-tts",{"type":36,"amount":45,"per":38,"unit":39},{"value":46,"currency":25},0.85,"StepAudio 2.5 TTS — per 10,000 characters",[49,5],"speech",[51,52],"verified","no-markup",[],{"provider":5,"providerDisplayName":6,"endpoint":55,"displayName":56,"displayDescription":57,"price":58,"categories":62,"tags":63,"supportedX402Networks":64},"\u002Fvoices","List System Voices","List the built-in text-to-speech voices. Free.",{"type":59,"amount":60},"PER_CALL",{"value":61,"currency":25},0,[49,5],[51,52],[65,66],"eip155:8453","eip155:143",{"provider":5,"providerDisplayName":6,"endpoint":68,"displayName":69,"displayDescription":70,"price":71,"categories":73,"tags":74,"supportedX402Networks":75},"\u002Fvoices\u002Fpreview","Preview Cloned Voice","Hear a short line in a recording's voice before cloning it. Free.",{"type":59,"amount":72},{"value":61,"currency":25},[49,5],[51,52],[],{"provider":5,"providerDisplayName":6,"endpoint":77,"displayName":78,"displayDescription":79,"price":80,"categories":83,"tags":84,"supportedX402Networks":85},"\u002Fvoices\u002Fclone","Clone Voice","Clone a voice from a 5-10 s recording into a reusable voice id.",{"type":59,"amount":81},{"value":82,"currency":25},1.5,[49,5],[51,52],[],[87,123,130],{"id":15,"displayName":88,"description":89,"endpointCount":90,"noMarkup":12,"kind":91,"children":92},"Gen AI","Tools to generate and process with AI, including images, video, speech, embeddings, and more.",139,"top",[93,94,95,96,97,98,49,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,5,120,121,122],"heygen","image-generation","video-generation","video-enhancement","image-enhancement","music-generation","audio","3d-generation","embeddings","chat","decision-models","agents","model-benchmarks","alibaba","artificial-analysis","bytedance","elevenlabs","fishaudio","gemini","heurist","kling","lmarena","magichour","minimax","mint","octen","openai","suzanne","topaz","typesafe",{"id":49,"displayName":124,"description":125,"shortDescription":126,"endpointCount":127,"noMarkup":12,"kind":128,"parents":129},"Speech & Voice","Tools to work with voice, including text-to-speech, transcription, dialogue, and more.","Text-to-speech, transcription and spoken dialogue.",26,"category",[15],{"id":5,"displayName":6,"description":7,"shortDescription":8,"url":9,"docsUrl":10,"endpointCount":11,"noMarkup":12,"kind":13,"provider":5,"parents":131},[15],"2026-11-06T23:38:18.676Z",1794454567611]