1. iFlytek speech-to-text
Tokentone
  • Models
    • List models
      • Native OpenAI format
      • Native Gemini format
  • Images
    • Nano Banana
      • OpenAI chat format
    • Qwen format
      • Generate image
      • Edit image
    • Proprietary V1 image generation
      • Submit image generation task
      • Query image generation task
  • Chat
    • OpenAI endpoint
      • Responses format (next generation)
    • Anthropic endpoint
      • Native Claude format
  • Audio
    • Native OpenAI format
      • Audio transcription
      • Audio translation
      • Text-to-speech
    • iFlytek speech-to-text
      • URL audio async transcription
        POST
      • Asynchronous transcription via file stream
        POST
      • Query transcription result
        POST
    • Native Gemini format
      POST
  • Videos
    • Volcengine endpoint
      • Create a video generation task.
      • Query video generation task status and results.
      • Upload asset
      • Query asset details
    • Proprietary V1 video generation
      • Custom voice (TK)
        • Create Kling custom voice
        • Query custom voice task
      • Submit video generation task
      • Query video generation task
  • Embeddings
    • Native OpenAI format
      POST
    • Native Gemini format
      POST
  • Completions
    • Native OpenAI format
      POST
  • Realtime
    • Native OpenAI format
      GET
  • Rerank
    • Document reranking
      POST
  • Moderations
    • Native OpenAI format
      POST
  • Schemas
    • Schemas
      • User
      • Log
      • Token
      • PageInfo
      • Channel
      • Redemption
      • ApiResponse
      • ChatCompletionStreamResponse
      • ResponsesStreamResponse
      • ImageGenerationRequest
      • ImageEditRequest
      • AudioTranscriptionRequest
      • AudioTranslationRequest
      • VideoRequest
      • VideoResponse
      • VideoTaskResponse
      • VideoTaskMetadata
      • VideoTaskError
      • OpenAIVideo
      • OpenAIVideoError
    • Schemas
      • ApiResponse
      • PageInfo
      • User
      • Channel
      • Token
      • Redemption
      • Log
    • Model
    • key
    • ModelsResponse
    • CreateVideoTaskRequest
    • Message
    • ResponseEntityTencentTkCustomVoiceOrderResponse
    • MessageContent
    • OpenAiImageDataItem
    • Tool
    • ResponseEntityTencentTkCustomVoiceTaskQueryResponse
    • ToolCall
    • GeminiModelsResponse
    • ConfirmAigcEventsRequest
    • ChatCompletionResponse
    • AigcEventOutputFileDto
    • ChatCompletionRequest
    • ResponseEntity?
    • CompletionRequest
    • CompletionResponse
    • GptprotoMessageDto
    • ResponseFormat
    • TableDataInfo
    • ResponsesRequest
    • ResponsesResponse
    • ClaudeRequest
    • ClaudeMessage
    • ClaudeResponse
    • GeminiContentPartDto
    • EmbeddingRequest
    • ModelMap
    • EmbeddingResponse
    • VideoContentPart
    • ImageResponse
    • ChatInputAudioDto
    • AudioTranscriptionResponse
    • TencentTkCustomVoiceOrderRequest
    • SpeechRequest
    • OpenAiImageUsageTokenDetails
    • RerankRequest
    • AigcTaskDetailDto
    • RerankResponse
    • AigcEventItemDto
    • ModerationRequest
    • ModerationResponse
    • GeminiRequest
    • AjaxResult
    • GeminiResponse
    • ResponseEntityArkCreateContentsGenerationsTasksResponse
    • ResponseEntityTkVideoOrderResponse
    • IflyUrlProcessRequest
    • GeminiContentDto
    • ResponseEntityTkCustomVoiceOrderResponse
    • MediaUrl
    • ResponseEntityTkCustomVoiceTaskQueryResponse
    • ChatPartDto
    • ArkContentsGenerationsTaskError
    • OpenAiImageUsage
    • TkVideoFileInfo
    • GoogleGeminiPartDto
    • ResponseEntityTkVideoTaskQueryResponse
    • IflyAudioMeta
    • GptprotoImageGenerateRequest
    • TkCustomVoiceOrderRequest
    • ManageAiModelSaveRequest
    • ArkContentsGenerationsTaskContent
    • TkVideoSubjectInfo
    • IflyProperty
    • key
    • ArkContentsGenerationsTaskUsage
    • CreateVideoTaskResponse
    • ChatFunctionCallDto
    • ArkVideoTool
    • TencentTkVoiceRef
    • TkVoiceRef
    • ResponseEntityOpenAiImagesResponse
    • ResponseEntityArkGetContentsGenerationsTaskResponse
    • TkVideoOrderRequest
    • GoogleGeminiContentDto
    • IflyResultQueryRequest
    • OutputItem
    • ManageAiSupplierSaveRequest
    • ServerToolUse
    • IflyFileProcessRequest
    • Usage
    • ErrorResponse
    • GetVideoTaskResponse
    • ArkVideoContentPart
    • ChatToolCallDto
    • ArkCreateContentsGenerationsTasksRequest
    • GptprotoViduPredictionResponse
    • IflyPlatformSubmitResponse
    • OpenAiImageInputReference
    • GatewayErrorResponse
    • OpenAiImageGenerationRequest
    • MapString
    • CreateContentsGenerationsAssetRequest
    • GptprotoChatRequest
    • IflyPlatformQueryResponse
    • ManageWalletRechargeRequest
    • VolcengineGetAssetRequest
    • GoogleGeminiEmbedContentRequest
    • IflyTaskResultData
    • TencentTkVideoOutputConfigDto
    • TencentTkVideoSubjectInfo
    • AiVideoOrderResponse
    • AigcVideoTaskInputFileInfoDto
    • AigcVideoOutputConfigDto
    • AiVideoOrderRequest
    • GeminiUsageMetadataDto
    • GeminiCandidateDto
    • GeminiGenerateContentResponse
    • GeminiThinkingConfigDto
    • HttpStatusCode
    • CreateAigcImageResponse
    • AigcImageTaskInputFileInfoDto
    • AigcImageOutputConfigDto
    • CreateAigcImageRequest
    • TaskContent
    • CitationItem
    • ContentBlock
    • ClaudeWebSearchResponse
    • MessageItem
    • UserLocation
    • WebSearchToolItem
    • ClaudeWebSearchRequest
    • ChatMessageDto
    • CreateAigcApiTokenResponse
    • CreateAigcApiTokenRequest
    • ClaudeFileAnalysisResponse
    • CacheControl
    • DocumentSourceWrapper
    • CitationsConfig
    • ContentBlock
    • ClaudeFileAnalysisRequest
    • Container
    • ClaudeTextToTextResponse
    • ToolItem
    • ClaudeTextToTextRequest
    • ArkMediaUrl
    • PredictionData
    • GptprotoViduImageToVideoRequest
    • OpenAiImageEditRequest
    • GoogleGeminiInlineBlobDto
    • GoogleGeminiFileDataDto
    • GoogleGeminiGenerationConfigDto
    • GoogleGeminiGenerateContentRequest
    • DescribeTaskDetailResponse
    • DescribeTaskDetailRequest
    • PullAigcEventsResponse
    • GoogleGeminiFunctionCallDto
    • GoogleGeminiFunctionResponseDto
    • GoogleGeminiExecutableCodeDto
    • GoogleGeminiCodeExecutionResultDto
    • GoogleGeminiFunctionCallingConfigDto
    • GoogleGeminiLatLngDto
    • GoogleGeminiRetrievalConfigDto
    • GoogleGeminiToolConfigDto
    • GoogleGeminiThinkingConfigDto
    • GoogleGeminiSafetySettingDto
    • AiImageOrderResponse
    • AiImageOrderRequest
    • GptprotoChoiceDto
    • GptprotoUsageDto
    • GptprotoChatResponse
    • CacheControlEphemeral
    • JsonSchemaFormat
    • OutputConfig
    • ToolChoice
    • ImageDataItem
    • AiTextOrderResponse
    • GptprotoImageGenerateResponse
    • MapObject
    • MessageParam
    • AiTextOrderRequest
    • Metadata
    • ThinkingConfig
    • InputSchema
    • CitationsConfigParam
    • ToolDefinition
    • ManageAiModelPriceSaveRequest
    • AnthropicMessagesCreateRequest
    • CreateAigcVideoResponse
    • CreateAigcVideoRequest
    • ResponseEntityTencentTkVideoOrderResponse
    • TencentTkVideoFileInfo
    • TencentTkVideoOrderRequest
    • ResponseEntityTencentTkVideoTaskQueryResponse
    • GeminiGenerationConfigDto
    • TaskUsage
    • ManageAiModelVendorSaveRequest
    • GeminiGenerateContentRequest
    • TaskError
    • GoogleGeminiSystemInstructionDto
    • ContentBlockParam
    • ManageAiCustomerTokenSaveRequest
    • CreateAssetRequest
    • key
    • StringOrContentBlocks
    • ManageAiModelSupplierRouteSaveRequest
    • IflyAsrcSegment
    • key
    • key
    • ResponseEntityStreamingResponseBody
    • TextCitationParam
    • TextBlockParam
    • key
    • StringOrTextBlocks
    • ResponseEntityTencentTkImageOrderResponse
    • GoogleGeminiCodeExecutionToolDto
    • TencentTkImageFileInfo
    • MapJsonNode
    • TencentTkImageOrderRequest
    • GoogleGeminiToolDto
    • ResponseEntityTencentTkImageTaskQueryResponse
    • VolcengineMediaUrl
    • VolcengineVideoContentPart
    • VolcengineVideoTool
    • VolcengineCreateVideoTaskRequest
    • ConversationModelOption
    • ConversationSessionItem
    • ConversationMessageItem
    • ConversationSendRequest
    • Handler
    • MediaType
    • DataWithMediaType
    • Throwable
    • StackTraceElement
    • Runnable
    • DefaultCallback
    • ErrorCallback
    • SseEmitter
    • ConversationImageOrderRequest
    • ConversationVideoOrderRequest
    • CitationItem
    • Usage
    • MessageItem
    • key
    • key
    • CitationItem
    • ContentBlock
    • Usage
    • ContentBlock
    • MessageItem
    • GoogleGeminiGenerateContentPayloadDto
    • GoogleGeminiCountTokensRequest
    • GoogleGeminiCreateCachedContentRequest
    • GoogleGeminiPatchCachedContentRequest
    • AccountAiCustomerTokenCreateRequest
    • ResponseEntityMapObject
  1. iFlytek speech-to-text

Query transcription result

POST
/tk/v1/ifly/async/result
Query transcription progress and results by task id. data.status=1 means transcription in progress—continue polling; data.status=2 means transcription complete—parse data.asrcResult to obtain text.

Request

Header Params

Body Params application/jsonRequired

Example
{
    "id": "music-weinierlai-demo-001"
}

Request Code Samples

Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
Request Request Example
Shell
JavaScript
Java
Swift
curl --location '/tk/v1/ifly/async/result' \
--header 'Authorization: Bearer sk-****' \
--header 'Content-Type: application/json' \
--data '{
    "id": "music-weinierlai-demo-001"
}'

Responses

🟢200
application/json
Query call successful (includes business states such as transcribing, completed, record not found, etc.)
Bodyapplication/json

Examples
{
    "code": "200",
    "msg": "Call succeeded",
    "data": {
        "id": "bb01aae1c08f43a89630dc4827880165",
        "bizId": "music-weinierlai-demo-001",
        "status": 1,
        "description": "Call succeeded",
        "asrcDesc": "Transcribing",
        "createTime": "2026-06-30 17:45:42",
        "updateTime": "2026-06-30 17:45:50"
    },
    "traceId": "67c451c3-6fa9-42f3-8fce-693abab2d247"
}
🟠400
🟠401
🔴503
Modified at 2026-07-15 15:01:15
Previous
Asynchronous transcription via file stream
Next
Native Gemini format
Built with