Skip to main content

Next
0.8.x
0.7.x
0.6.x
0.5.x
0.4.x
0.3.x
0.2.x
0.1.x

Getting Started

Frequently Asked Questions

Glossary of Terms

Natural Language Processing

usePrivacyFilter

useSpeechToText

useTextEmbeddings

useTextToSpeech

Computer Vision

useClassification

useImageEmbeddings

useInstanceSegmentation

useObjectDetection

usePoseEstimation

useSemanticSegmentation

useStyleTransfer

VisionCamera Integration

ExecuTorch Bindings

useExecutorchModule

Natural Language Processing

PrivacyFilterModule

SpeechToTextModule

TextEmbeddingsModule

TextToSpeechModule

TokenizerModule

Computer Vision

ClassificationModule

ImageEmbeddingsModule

InstanceSegmentationModule

ObjectDetectionModule

PoseEstimationModule

SemanticSegmentationModule

StyleTransferModule

TextToImageModule

VerticalOCRModule

ExecuTorch Bindings

ExecutorchModule

Resource Fetcher

Abstract Class: BaseResourceFetcherClass\<TDownload\>

Class: ClassificationModule\<T\>

Class: ExecutorchModule

Class: ImageEmbeddingsModule

Class: InstanceSegmentationModule\<T\>

Class: LLMModule

Class: MessageCountContextStrategy

Class: NoopContextStrategy

Class: OCRModule

Class: ObjectDetectionModule\<T\>

Class: PoseEstimationModule\<T\>

Class: PrivacyFilterModule

Class: ResourceFetcher

Class: RnExecutorchError

Class: SemanticSegmentationModule\<T\>

Class: SlidingWindowContextStrategy

Class: SpeechToTextModule

Class: StyleTransferModule

Class: TextEmbeddingsModule

Class: TextToImageModule

Class: TextToSpeechModule

Class: TokenizerModule

Class: VADModule

Class: VerticalOCRModule

Enumeration: CocoKeypoint

Enumeration: CocoLabel

Enumeration: CocoLabelYolo

Enumeration: DeeplabLabel

Enumeration: DownloadStatus

Enumeration: FastSAMLabel

Enumeration: HTTP\_CODE

Enumeration: Imagenet1kLabel

Enumeration: RnExecutorchErrorCode

Enumeration: ScalarType

Enumeration: SelfieSegmentationLabel

Enumeration: SourceType

Function: DEFAULT\_STRUCTURED\_OUTPUT\_PROMPT()

Function: cleanupExecutorch()

Function: fixAndValidateStructuredOutput()

Function: getModelNameForUrl()

Function: getStructuredOutputPrompt()

Function: initExecutorch()

Function: selectByBox()

Function: selectByPoint()

Function: selectByText()

Function: styleTransferUrls()

Function: useClassification()

Function: useExecutorchModule()

Function: useImageEmbeddings()

Function: useInstanceSegmentation()

Function: useLLM()

Function: useOCR()

Function: useObjectDetection()

Function: usePoseEstimation()

Function: usePrivacyFilter()

Function: useSemanticSegmentation()

Function: useSpeechToText()

Function: useStyleTransfer()

Function: useTextEmbeddings()

Function: useTextToImage()

Function: useTextToSpeech()

Function: useTokenizer()

Function: useVAD()

Function: useVerticalOCR()

react-native-executorch

Interface: Bbox

Interface: ChatConfig

Interface: ClassificationProps\<C\>

Interface: ClassificationType\<L\>

Interface: ContextStrategy

Interface: DecodingOptions

Interface: Detection\<L\>

Interface: ExecutorchConfig

Interface: ExecutorchModuleProps

Interface: ExecutorchModuleType

Interface: Frame

Interface: GenerationConfig

Interface: ImageEmbeddingsProps

Interface: ImageEmbeddingsType

Interface: InstanceSegmentationOptions\<L\>

Interface: InstanceSegmentationProps\<C\>

Interface: InstanceSegmentationType\<L\>

Interface: Keypoint

Interface: LLMConfig

Interface: LLMProps

Interface: LLMType

Interface: LLMTypeBase

Interface: LLMTypeMultimodal\<C\>

Interface: Message

Interface: NativeSegmentedInstance

Interface: OCRDetection

Interface: OCRProps

Interface: OCRType

Interface: ObjectDetectionOptions\<L\>

Interface: ObjectDetectionProps\<C\>

Interface: ObjectDetectionType\<L\>

Interface: PiiEntity

Interface: PixelData

Interface: PoseEstimationOptions

Interface: PoseEstimationProps\<C\>

Interface: PoseEstimationType\<K\>

Interface: PrivacyFilterModelSources

Interface: PrivacyFilterProps

Interface: PrivacyFilterType

Interface: ResourceFetcherAdapter

Interface: Segment

Interface: SegmentedInstance\<L\>

Interface: SemanticSegmentationProps\<C\>

Interface: SemanticSegmentationType\<L\>

Interface: SpeechToTextModelConfig

Interface: SpeechToTextProps

Interface: SpeechToTextType

Interface: StreamingOptions

Interface: StyleTransferProps

Interface: StyleTransferType

Interface: TensorPtr

Interface: TextEmbeddingsProps

Interface: TextEmbeddingsType

Interface: TextToImageProps

Interface: TextToImageType

Interface: TextToSpeechInput

Interface: TextToSpeechModelConfig

Interface: TextToSpeechPhonemizerConfig

Interface: TextToSpeechStreamingCallbacks

Interface: TextToSpeechStreamingInput

Interface: TextToSpeechType

Interface: TokenizerProps

Interface: TokenizerType

Interface: ToolCall

Interface: ToolsConfig

Interface: TranscriptionResult

Interface: TranscriptionSegment

Interface: VADConfig

Interface: VADProps

Interface: VADStreamingInput

Interface: VADStreamingOptions

Interface: VADType

Interface: VerticalOCRProps

Interface: ViterbiBiases

Interface: Word

react-native-executorch

ResourceFetcherUtils

Function: calculateDownloadProgress()

Function: getFilenameFromUri()

Function: hashObject()

Function: isEmulator()

Function: isUrlHfRepo()

Function: removeFilePrefix()

Function: triggerDownloadEvent()

Function: triggerHuggingFaceDownloadCounter()

Type Alias: Backend

Type Alias: ClassificationConfig\<T\>

Type Alias: ClassificationLabels\<M\>

Type Alias: ClassificationModelName

Type Alias: ClassificationModelSources

Type Alias: ImageEmbeddingsModelName

Type Alias: InstanceModelNameOf\<C\>

Type Alias: InstanceSegmentationConfig\<T\>

Type Alias: InstanceSegmentationLabels\<M\>

Type Alias: InstanceSegmentationModelName

Type Alias: InstanceSegmentationModelSources

Type Alias: LLMCapability

Type Alias: LLMModelName

Type Alias: LLMTool

Type Alias: LabelEnum

Type Alias: MediaArg\<C\>

Type Alias: MessageRole

Type Alias: ModelNameOf\<C\>

Type Alias: ModelOpts\<B\>

Type Alias: OCRLanguage

Type Alias: OCRModelName

Type Alias: ObjectDetectionConfig\<T\>

Type Alias: ObjectDetectionLabels\<M\>

Type Alias: ObjectDetectionModelName

Type Alias: ObjectDetectionModelSources

Type Alias: PersonKeypoints\<K\>

Type Alias: PoseDetections\<K\>

Type Alias: PoseEstimationConfig\<K\>

Type Alias: PoseEstimationKeypoints\<M\>

Type Alias: PoseEstimationModelName

Type Alias: PoseEstimationModelSources

Type Alias: PrivacyFilterModelName

Type Alias: ResourceSource

Type Alias: SegmentationLabels\<M\>

Type Alias: SemanticSegmentationConfig\<T\>

Type Alias: SemanticSegmentationModelName

Type Alias: SemanticSegmentationModelSources

Type Alias: SpeechToTextLanguage

Type Alias: SpeechToTextModelName

Type Alias: StyleTransferModelName

Type Alias: TensorBuffer

Type Alias: TextEmbeddingsModelName

Type Alias: TextToImageModelName

Type Alias: TextToSpeechLanguage

Type Alias: TextToSpeechModelName

Type Alias: TextToSpeechModelSources

Type Alias: Triple\<T\>

Type Alias: VADModelName

Variable: ALL\_MINILM\_L6\_V2

Variable: ALL\_MPNET\_BASE\_V2

Variable: BIELIK\_V3\_0\_1\_5B

Variable: BIELIK\_V3\_0\_1\_5B\_QUANTIZED

Variable: BK\_SDM\_TINY\_VPRED\_256

Variable: BK\_SDM\_TINY\_VPRED\_512

Variable: CLIP\_VIT\_BASE\_PATCH32\_IMAGE

Variable: CLIP\_VIT\_BASE\_PATCH32\_IMAGE\_QUANTIZED

Variable: CLIP\_VIT\_BASE\_PATCH32\_TEXT

Variable: DEEPLAB\_V3\_MOBILENET\_V3\_LARGE

Variable: DEEPLAB\_V3\_MOBILENET\_V3\_LARGE\_QUANTIZED

Variable: DEEPLAB\_V3\_RESNET101

Variable: DEEPLAB\_V3\_RESNET101\_QUANTIZED

Variable: DEEPLAB\_V3\_RESNET50

Variable: DEEPLAB\_V3\_RESNET50\_QUANTIZED

Variable: DEFAULT\_CHAT\_CONFIG

Variable: DEFAULT\_CONTEXT\_BUFFER\_TOKENS

Variable: DEFAULT\_MESSAGE\_HISTORY

Variable: DEFAULT\_SYSTEM\_PROMPT

~~Variable: DISTILUSE\_BASE\_MULTILINGUAL\_CASED\_V2\_8DA4W~~

Variable: DISTILUSE\_BASE\_MULTILINGUAL\_CASED\_V2\_8DA4W\_MODEL

Variable: DISTILUSE\_BASE\_MULTILINGUAL\_CASED\_V2\_TOKENIZER

Variable: EFFICIENTNET\_V2\_S

Variable: EFFICIENTNET\_V2\_S\_COREML\_FP16\_MODEL

Variable: EFFICIENTNET\_V2\_S\_COREML\_FP32\_MODEL

Variable: EFFICIENTNET\_V2\_S\_QUANTIZED

Variable: EFFICIENTNET\_V2\_S\_XNNPACK\_FP32\_MODEL

Variable: EFFICIENTNET\_V2\_S\_XNNPACK\_INT8\_MODEL

Variable: FASTSAM\_S

Variable: FASTSAM\_S\_COREML\_FP16\_MODEL

Variable: FASTSAM\_S\_XNNPACK\_FP32\_MODEL

Variable: FASTSAM\_X

Variable: FASTSAM\_X\_COREML\_FP16\_MODEL

Variable: FASTSAM\_X\_XNNPACK\_FP32\_MODEL

Variable: FCN\_RESNET101

Variable: FCN\_RESNET101\_QUANTIZED

Variable: FCN\_RESNET50

Variable: FCN\_RESNET50\_QUANTIZED

Variable: FSMN\_VAD

Variable: HAMMER2\_1\_0\_5B

Variable: HAMMER2\_1\_0\_5B\_QUANTIZED

Variable: HAMMER2\_1\_1\_5B

Variable: HAMMER2\_1\_1\_5B\_QUANTIZED

Variable: HAMMER2\_1\_3B

Variable: HAMMER2\_1\_3B\_QUANTIZED

Variable: IMAGENET1K\_MEAN

Variable: IMAGENET1K\_STD

Variable: KOKORO\_AMERICAN\_ENGLISH\_FEMALE\_HEART

Variable: KOKORO\_AMERICAN\_ENGLISH\_FEMALE\_RIVER

Variable: KOKORO\_AMERICAN\_ENGLISH\_FEMALE\_SARAH

Variable: KOKORO\_AMERICAN\_ENGLISH\_MALE\_ADAM

Variable: KOKORO\_AMERICAN\_ENGLISH\_MALE\_MICHAEL

Variable: KOKORO\_AMERICAN\_ENGLISH\_MALE\_SANTA

Variable: KOKORO\_BRITISH\_ENGLISH\_FEMALE\_EMMA

Variable: KOKORO\_BRITISH\_ENGLISH\_MALE\_DANIEL

Variable: KOKORO\_FRENCH\_FEMALE\_SIWIS

Variable: KOKORO\_GERMAN

Variable: KOKORO\_GERMAN\_FEMALE\_ANNA

Variable: KOKORO\_HINDI\_FEMALE\_ALPHA

Variable: KOKORO\_HINDI\_MALE\_OMEGA

Variable: KOKORO\_HINDI\_MALE\_PSI

Variable: KOKORO\_ITALIAN\_FEMALE\_SARA

Variable: KOKORO\_ITALIAN\_MALE\_NICOLA

Variable: KOKORO\_POLISH

Variable: KOKORO\_POLISH\_MALE\_MATEUSZ

Variable: KOKORO\_PORTUGUESE\_FEMALE\_DORA

Variable: KOKORO\_PORTUGUESE\_MALE\_SANTA

Variable: KOKORO\_SPANISH\_FEMALE\_DORA

Variable: KOKORO\_SPANISH\_MALE\_ALEX

Variable: KOKORO\_STANDARD

Variable: LFM2\_5\_1\_2B\_INSTRUCT

Variable: LFM2\_5\_1\_2B\_INSTRUCT\_QUANTIZED

Variable: LFM2\_5\_350M

Variable: LFM2\_5\_350M\_QUANTIZED

Variable: LFM2\_5\_VL\_1\_6B\_QUANTIZED

Variable: LFM2\_5\_VL\_450M\_QUANTIZED

~~Variable: LFM2\_VL\_1\_6B\_QUANTIZED~~

~~Variable: LFM2\_VL\_450M\_QUANTIZED~~

Variable: LLAMA3\_2\_1B

~~Variable: LLAMA3\_2\_1B\_QLORA~~

Variable: LLAMA3\_2\_1B\_SPINQUANT

Variable: LLAMA3\_2\_3B

~~Variable: LLAMA3\_2\_3B\_QLORA~~

Variable: LLAMA3\_2\_3B\_SPINQUANT

Variable: LRASPP\_MOBILENET\_V3\_LARGE

Variable: LRASPP\_MOBILENET\_V3\_LARGE\_QUANTIZED

Variable: MULTI\_QA\_MINILM\_L6\_COS\_V1

Variable: MULTI\_QA\_MPNET\_BASE\_DOT\_V1

Variable: OCR\_ABAZA

Variable: OCR\_ADYGHE

Variable: OCR\_AFRIKAANS

Variable: OCR\_ALBANIAN

Variable: OCR\_AVAR

Variable: OCR\_AZERBAIJANI

Variable: OCR\_BELARUSIAN

Variable: OCR\_BOSNIAN

Variable: OCR\_BULGARIAN

Variable: OCR\_CHECHEN

Variable: OCR\_CROATIAN

Variable: OCR\_CZECH

Variable: OCR\_DANISH

Variable: OCR\_DARGWA

Variable: OCR\_DUTCH

Variable: OCR\_ENGLISH

Variable: OCR\_ESTONIAN

Variable: OCR\_FRENCH

Variable: OCR\_GERMAN

Variable: OCR\_HUNGARIAN

Variable: OCR\_ICELANDIC

Variable: OCR\_INDONESIAN

Variable: OCR\_INGUSH

Variable: OCR\_IRISH

Variable: OCR\_ITALIAN

Variable: OCR\_JAPANESE

Variable: OCR\_KANNADA

Variable: OCR\_KARBADIAN

Variable: OCR\_KOREAN

Variable: OCR\_KURDISH

Variable: OCR\_LAK

Variable: OCR\_LATIN

Variable: OCR\_LATVIAN

Variable: OCR\_LEZGHIAN

Variable: OCR\_LITHUANIAN

Variable: OCR\_MALAY

Variable: OCR\_MALTESE

Variable: OCR\_MAORI

Variable: OCR\_MONGOLIAN

Variable: OCR\_NORWEGIAN

Variable: OCR\_OCCITAN

Variable: OCR\_PALI

Variable: OCR\_POLISH

Variable: OCR\_PORTUGUESE

Variable: OCR\_ROMANIAN

Variable: OCR\_RUSSIAN

Variable: OCR\_SERBIAN\_CYRILLIC

Variable: OCR\_SERBIAN\_LATIN

Variable: OCR\_SIMPLIFIED\_CHINESE

Variable: OCR\_SLOVAK

Variable: OCR\_SLOVENIAN

Variable: OCR\_SPANISH

Variable: OCR\_SWAHILI

Variable: OCR\_SWEDISH

Variable: OCR\_TABASSARAN

Variable: OCR\_TAGALOG

Variable: OCR\_TAJIK

Variable: OCR\_TELUGU

Variable: OCR\_TURKISH

Variable: OCR\_UKRAINIAN

Variable: OCR\_UZBEK

Variable: OCR\_VIETNAMESE

Variable: OCR\_WELSH

Variable: PARAPHRASE\_MULTILINGUAL\_MINILM\_L12\_V2\_QUANTIZED

Variable: PHI\_4\_MINI\_4B

Variable: PHI\_4\_MINI\_4B\_QUANTIZED

Variable: PRIVACY\_FILTER\_NEMOTRON

Variable: PRIVACY\_FILTER\_OPENAI

Variable: QWEN2\_5\_0\_5B

Variable: QWEN2\_5\_0\_5B\_QUANTIZED

Variable: QWEN2\_5\_1\_5B

Variable: QWEN2\_5\_1\_5B\_QUANTIZED

Variable: QWEN2\_5\_3B

Variable: QWEN2\_5\_3B\_QUANTIZED

Variable: QWEN3\_0\_6B

Variable: QWEN3\_0\_6B\_QUANTIZED

Variable: QWEN3\_1\_7B

Variable: QWEN3\_1\_7B\_QUANTIZED

Variable: QWEN3\_4B

Variable: QWEN3\_4B\_QUANTIZED

Variable: QWEN3\_5\_0\_8B\_QUANTIZED

Variable: QWEN3\_5\_2B\_QUANTIZED

Variable: RF\_DETR\_NANO

Variable: RF\_DETR\_NANO\_COREML\_INT8\_MODEL

Variable: RF\_DETR\_NANO\_SEG

Variable: RF\_DETR\_NANO\_SEG\_COREML\_INT8\_MODEL

Variable: RF\_DETR\_NANO\_SEG\_XNNPACK\_FP32\_MODEL

Variable: RF\_DETR\_NANO\_XNNPACK\_FP32\_MODEL

Variable: SELFIE\_SEGMENTATION

Variable: SMOLLM2\_1\_135M

Variable: SMOLLM2\_1\_135M\_QUANTIZED

Variable: SMOLLM2\_1\_1\_7B

Variable: SMOLLM2\_1\_1\_7B\_QUANTIZED

Variable: SMOLLM2\_1\_360M

Variable: SMOLLM2\_1\_360M\_QUANTIZED

Variable: SPECIAL\_TOKENS

Variable: SSDLITE\_320\_MOBILENET\_V3\_LARGE

Variable: SSDLITE\_320\_MOBILENET\_V3\_LARGE\_COREML\_FP16\_MODEL

Variable: SSDLITE\_320\_MOBILENET\_V3\_LARGE\_XNNPACK\_FP32\_MODEL

Variable: STYLE\_TRANSFER\_CANDY

Variable: STYLE\_TRANSFER\_CANDY\_QUANTIZED

Variable: STYLE\_TRANSFER\_MOSAIC

Variable: STYLE\_TRANSFER\_MOSAIC\_QUANTIZED

Variable: STYLE\_TRANSFER\_RAIN\_PRINCESS

Variable: STYLE\_TRANSFER\_RAIN\_PRINCESS\_QUANTIZED

Variable: STYLE\_TRANSFER\_UDNIE

Variable: STYLE\_TRANSFER\_UDNIE\_QUANTIZED

Variable: WHISPER\_BASE

Variable: WHISPER\_BASE\_EN

Variable: WHISPER\_BASE\_EN\_MODEL\_COREML

Variable: WHISPER\_BASE\_EN\_MODEL\_XNNPACK

Variable: WHISPER\_BASE\_EN\_TOKENIZER

Variable: WHISPER\_BASE\_MODEL\_COREML

Variable: WHISPER\_BASE\_MODEL\_XNNPACK

Variable: WHISPER\_BASE\_TOKENIZER

Variable: WHISPER\_SMALL

Variable: WHISPER\_SMALL\_EN

Variable: WHISPER\_SMALL\_EN\_MODEL\_COREML

Variable: WHISPER\_SMALL\_EN\_MODEL\_XNNPACK

Variable: WHISPER\_SMALL\_EN\_TOKENIZER

Variable: WHISPER\_SMALL\_MODEL\_COREML

Variable: WHISPER\_SMALL\_MODEL\_XNNPACK

Variable: WHISPER\_SMALL\_TOKENIZER

Variable: WHISPER\_TINY

Variable: WHISPER\_TINY\_EN

Variable: WHISPER\_TINY\_EN\_MODEL\_COREML

Variable: WHISPER\_TINY\_EN\_MODEL\_XNNPACK

Variable: WHISPER\_TINY\_EN\_TOKENIZER

Variable: WHISPER\_TINY\_MODEL\_COREML

Variable: WHISPER\_TINY\_MODEL\_XNNPACK

Variable: WHISPER\_TINY\_TOKENIZER

Variable: YOLO26L

Variable: YOLO26L\_SEG

Variable: YOLO26M

Variable: YOLO26M\_SEG

Variable: YOLO26N

Variable: YOLO26N\_POSE

Variable: YOLO26N\_SEG

Variable: YOLO26S

Variable: YOLO26S\_SEG

Variable: YOLO26X

Variable: YOLO26X\_SEG

Variable: isAvailable

Variable: models

Variable: parseToolCall()

This is unreleased documentation for React Native ExecuTorch Next version.

For up-to-date documentation, see the latest version (0.8.x).

API Reference
variables
Variable: KOKORO\_AMERICAN\_ENGLISH\_FEMALE\_SARAH

Version: Next

Variable: KOKORO_AMERICAN_ENGLISH_FEMALE_SARAH

const KOKORO_AMERICAN_ENGLISH_FEMALE_SARAH: TextToSpeechModelConfig

Defined in: constants/tts/voices.ts:79

Variable: KOKORO\_AMERICAN\_ENGLISH\_FEMALE\_RIVER

Variable: KOKORO\_AMERICAN\_ENGLISH\_MALE\_ADAM

© Software Mansion 2026. All trademarks and copyrights belong to their respective owners.