cjwbw/seamless_communication

SeamlessM4T—Massively Multilingual & Multimodal Machine Translation

Capabilities

No capability data available

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`input_audio`	string(uri)	Provide input file for tasks with speech input: S2ST, S2TT and ASR.	`—`	—
`input_text`	string	Provide input for tasks with text: T2ST and T2TT.	`—`	—
`input_text_language`	string	Specify language of the input_text for T2ST and T2TT	`"None"`	NoneAfrikaansAmharicArmenianAssameseBasqueBelarusianBengaliBosnianBulgarianBurmeseCantoneseCatalanCebuanoCentral KurdishCroatianCzechDanishDutchEgyptian ArabicEnglishEstonianFinnishFrenchGalicianGandaGeorgianGermanGreekGujaratiHalh MongolianHebrewHindiHungarianIcelandicIgboIndonesianIrishItalianJapaneseJavaneseKannadaKazakhKhmerKoreanKyrgyzLaoLithuanianLuoMacedonianMaithiliMalayalamMalteseMandarin ChineseMarathiMeiteiModern Standard ArabicMoroccan ArabicNepaliNorth AzerbaijaniNorthern UzbekNorwegian BokmålNorwegian NynorskNyanjaOdiaPolishPortuguesePunjabiRomanianRussianSerbianShonaSindhiSlovakSlovenianSomaliSouthern PashtoSpanishStandard LatvianStandard MalaySwahiliSwedishTagalogTajikTamilTeluguThaiTurkishUkrainianUrduVietnameseWelshWest Central OromoWestern PersianYorubaZulu
`max_input_audio_length`	number	Set maximum input audio length.	`60`	—
`target_language_text_only`	string	Set target language for tasks with text output only: S2TT, T2TT and ASR.	`"Norwegian Nynorsk"`	AfrikaansAmharicArmenianAssameseBasqueBelarusianBengaliBosnianBulgarianBurmeseCantoneseCatalanCebuanoCentral KurdishCroatianCzechDanishDutchEgyptian ArabicEnglishEstonianFinnishFrenchGalicianGandaGeorgianGermanGreekGujaratiHalh MongolianHebrewHindiHungarianIcelandicIgboIndonesianIrishItalianJapaneseJavaneseKannadaKazakhKhmerKoreanKyrgyzLaoLithuanianLuoMacedonianMaithiliMalayalamMalteseMandarin ChineseMarathiMeiteiModern Standard ArabicMoroccan ArabicNepaliNorth AzerbaijaniNorthern UzbekNorwegian BokmålNorwegian NynorskNyanjaOdiaPolishPortuguesePunjabiRomanianRussianSerbianShonaSindhiSlovakSlovenianSomaliSouthern PashtoSpanishStandard LatvianStandard MalaySwahiliSwedishTagalogTajikTamilTeluguThaiTurkishUkrainianUrduVietnameseWelshWest Central OromoWestern PersianYorubaZulu
`target_language_with_speech`	string	Set target language for tasks with speech output: S2ST or T2ST. Less languages are available for speech compared to text output.	`"French"`	BengaliCatalanCzechDanishDutchEnglishEstonianFinnishFrenchGermanHindiIndonesianItalianJapaneseKoreanMalteseMandarin ChineseModern Standard ArabicNorthern UzbekPolishPortugueseRomanianRussianSlovakSpanishSwahiliSwedishTagalogTeluguThaiTurkishUkrainianUrduVietnameseWelshWestern Persian
`task_name`	string	Choose a task	`"S2ST (Speech to Speech translation)"`	S2ST (Speech to Speech translation)S2TT (Speech to Text translation)T2ST (Text to Speech translation)T2TT (Text to Text translation)ASR (Automatic Speech Recognition)

input_audiostring

Provide input file for tasks with speech input: S2ST, S2TT and ASR.

input_textstring

Provide input for tasks with text: T2ST and T2TT.

input_text_languagestring

Specify language of the input_text for T2ST and T2TT

Default: "None"

NoneAfrikaansAmharicArmenianAssameseBasqueBelarusianBengaliBosnianBulgarianBurmeseCantoneseCatalanCebuanoCentral KurdishCroatianCzechDanishDutchEgyptian ArabicEnglishEstonianFinnishFrenchGalicianGandaGeorgianGermanGreekGujaratiHalh MongolianHebrewHindiHungarianIcelandicIgboIndonesianIrishItalianJapaneseJavaneseKannadaKazakhKhmerKoreanKyrgyzLaoLithuanianLuoMacedonianMaithiliMalayalamMalteseMandarin ChineseMarathiMeiteiModern Standard ArabicMoroccan ArabicNepaliNorth AzerbaijaniNorthern UzbekNorwegian BokmålNorwegian NynorskNyanjaOdiaPolishPortuguesePunjabiRomanianRussianSerbianShonaSindhiSlovakSlovenianSomaliSouthern PashtoSpanishStandard LatvianStandard MalaySwahiliSwedishTagalogTajikTamilTeluguThaiTurkishUkrainianUrduVietnameseWelshWest Central OromoWestern PersianYorubaZulu

max_input_audio_lengthnumber

Set maximum input audio length.

Default: 60

target_language_text_onlystring

Set target language for tasks with text output only: S2TT, T2TT and ASR.

Default: "Norwegian Nynorsk"

AfrikaansAmharicArmenianAssameseBasqueBelarusianBengaliBosnianBulgarianBurmeseCantoneseCatalanCebuanoCentral KurdishCroatianCzechDanishDutchEgyptian ArabicEnglishEstonianFinnishFrenchGalicianGandaGeorgianGermanGreekGujaratiHalh MongolianHebrewHindiHungarianIcelandicIgboIndonesianIrishItalianJapaneseJavaneseKannadaKazakhKhmerKoreanKyrgyzLaoLithuanianLuoMacedonianMaithiliMalayalamMalteseMandarin ChineseMarathiMeiteiModern Standard ArabicMoroccan ArabicNepaliNorth AzerbaijaniNorthern UzbekNorwegian BokmålNorwegian NynorskNyanjaOdiaPolishPortuguesePunjabiRomanianRussianSerbianShonaSindhiSlovakSlovenianSomaliSouthern PashtoSpanishStandard LatvianStandard MalaySwahiliSwedishTagalogTajikTamilTeluguThaiTurkishUkrainianUrduVietnameseWelshWest Central OromoWestern PersianYorubaZulu

target_language_with_speechstring

Set target language for tasks with speech output: S2ST or T2ST. Less languages are available for speech compared to text output.

Default: "French"

BengaliCatalanCzechDanishDutchEnglishEstonianFinnishFrenchGermanHindiIndonesianItalianJapaneseKoreanMalteseMandarin ChineseModern Standard ArabicNorthern UzbekPolishPortugueseRomanianRussianSlovakSpanishSwahiliSwedishTagalogTeluguThaiTurkishUkrainianUrduVietnameseWelshWestern Persian

task_namestring

Choose a task

Default: "S2ST (Speech to Speech translation)"

S2ST (Speech to Speech translation)S2TT (Speech to Text translation)T2ST (Text to Speech translation)T2TT (Text to Text translation)ASR (Automatic Speech Recognition)

Version: 668a4fec05a8Updated: 7/25/2026100.2K runs