{"id":"bytedance/seed-speech-2","object":"model","type":"model","name":"Seed Speech 2","creator":"ByteDance","modality":"audio","tasks":["text-to-speech"],"description":"ByteDance's speech model, in Chinese and English.","revision":"2026-10-03","version":null,"latest":true,"status":"stable","deprecation":null,"pricing":{"unit":"character","usd":"0.0000405","overrides":[],"drivers":["text"]},"input_schema":{"type":"object","additionalProperties":false,"required":["text"],"properties":{"text":{"type":"string","title":"Text","minLength":1,"maxLength":5000,"pattern":"\\S","x-leap-ui":{"group":"main","order":0,"widget":"textarea"}},"voice":{"type":"string","title":"Voice","oneOf":[{"const":"stokie_en","title":"Stokie en"},{"const":"vivi_mixed_en_zh_ja_es_id","title":"Vivi mixed en zh ja es id"},{"const":"mindy_en_es_id_pt_zh","title":"Mindy en es id pt zh"},{"const":"dacey_en","title":"Dacey en"},{"const":"tim_en","title":"Tim en"},{"const":"kian_en_zh","title":"Kian en zh"},{"const":"cedric_en_zh","title":"Cedric en zh"},{"const":"sophie_en_zh","title":"Sophie en zh"},{"const":"jean_en_zh","title":"Jean en zh"},{"const":"magnus_en_zh","title":"Magnus en zh"},{"const":"mabel_en_zh","title":"Mabel en zh"},{"const":"nadia_en_zh","title":"Nadia en zh"},{"const":"opal_en_zh","title":"Opal en zh"},{"const":"pearl_en_zh","title":"Pearl en zh"},{"const":"quentin_en_zh","title":"Quentin en zh"},{"const":"vienna_mixed_en_zh","title":"Vienna mixed en zh"},{"const":"alina_mixed_en_zh","title":"Alina mixed en zh"},{"const":"corinne_mixed_en_zh","title":"Corinne mixed en zh"},{"const":"esther_mixed_en_zh","title":"Esther mixed en zh"},{"const":"freya_mixed_en_zh","title":"Freya mixed en zh"},{"const":"gigi_mixed_en_zh","title":"Gigi mixed en zh"},{"const":"holly_mixed_en_zh","title":"Holly mixed en zh"},{"const":"lyla_mixed_en_zh","title":"Lyla mixed en zh"},{"const":"daisy_mixed_en_zh","title":"Daisy mixed en zh"},{"const":"tracy_es_zh","title":"Tracy es zh"},{"const":"jess_ja_es_id_pt_en_zh","title":"Jess ja es id pt en zh"},{"const":"pinky_es_ko_mixed_en_zh","title":"Pinky es ko mixed en zh"},{"const":"sweety_ja_es","title":"Sweety ja es"},{"const":"sandy_es_mixed_en_zh","title":"Sandy es mixed en zh"},{"const":"sven_de","title":"Sven de"},{"const":"minimi_ja","title":"Minimi ja"},{"const":"usseau_fr","title":"Usseau fr"},{"const":"felipe_es","title":"Felipe es"},{"const":"han_id","title":"Han id"},{"const":"martins_pt","title":"Martins pt"},{"const":"enzo_it","title":"Enzo it"},{"const":"shane_ko","title":"Shane ko"},{"const":"bonnie_zh","title":"Bonnie zh"},{"const":"felix_zh","title":"Felix zh"},{"const":"celeste_zh","title":"Celeste zh"},{"const":"monkey_king_zh","title":"Monkey king zh"}],"default":"stokie_en","x-leap-ui":{"group":"main","order":5,"widget":"select"}},"settings":{"type":"object","title":"Model settings","additionalProperties":false,"default":{},"properties":{"sample_rate":{"type":"integer","title":"Sample Rate","enum":[8000,16000,22050,24000,32000,44100,48000],"x-leap-ui":{"group":"advanced","order":30,"widget":"select","help":"Sample rate of the output audio in Hz."},"default":24000},"speed":{"type":"number","title":"Speed","minimum":0.5,"maximum":2,"x-leap-ui":{"group":"advanced","order":31,"widget":"number","help":"Speech speed."},"default":1},"volume":{"type":"number","title":"Volume","minimum":0.5,"maximum":2,"x-leap-ui":{"group":"advanced","order":32,"widget":"number","help":"Volume."},"default":1},"pitch":{"type":"integer","title":"Pitch","minimum":-12,"maximum":12,"x-leap-ui":{"group":"advanced","order":33,"widget":"number","help":"Voice pitch shift in semitones."},"default":0},"language":{"type":"string","title":"Language","oneOf":[{"const":"zh","title":"Zh"},{"const":"en","title":"En"},{"const":"ja","title":"Ja"},{"const":"es-mx","title":"Es-mx"},{"const":"id","title":"Id"},{"const":"pt-br","title":"Pt-br"},{"const":"ko","title":"Ko"},{"const":"it","title":"It"},{"const":"de","title":"De"},{"const":"fr","title":"Fr"}],"x-leap-ui":{"group":"advanced","order":34,"widget":"select","help":"Force the text to be read as a single language, disabling automatic language detection."}}}}}}}