1. OpenAI
TikHub-AI-Proxy
  • 默认模块
    • Overview (PLEASE READ)
    • Streaming API
    • OpenAI
      • OpenAI response
        POST
      • OpenAI embeddings
        POST
      • OpenAI audio transcription
        POST
      • DeepSeek chat completion
        POST
      • OpenAI image generation
        POST
      • OpenAI image edit
        POST
      • OpenAI image edit (legacy alias)
        POST
      • Chat completion
        POST
    • Claude
      • Claude message
      • Claude chat completion
    • DeepSeek
      • DeepSeek chat completion
      • DeepSeek chat completion
    • Gemini
      • Gemini content
    • Kimi
      • Chat completion
    • Qwen
      • Chat completion
    • Schemas
      • ChatCompletionRequest
      • ImageGenerationRequest
      • ChatMessage
      • ImageEditRequest
      • Tool
      • ImageGenerationResponse
      • ToolCall
      • ChatCompletionResponse
      • ChatCompletionChoice
      • ContentFilterResults
      • UsageInfo
      • EmbeddingRequest
      • EmbeddingResponse
      • TranscriptionRequest
      • TranscriptionResponse
      • ClaudeMessageRequest
      • ClaudeMessageResponse
      • VideoCreateRequest
      • VideoResponse
      • VideoRemixRequest
      • GeminiGenerateContentRequest
      • VideoListResponse
      • ResponseRequest
      • GeminiContent
      • VideoDeleteResponse
      • GeminiGenerationConfig
      • GeminiGenerateContentResponse
      • ResponseObject
      • SeedanceTaskRequest
      • SeedanceTaskCreateResponse
      • SeedanceTaskResponse
      • KlingText2VideoRequest
      • KlingImage2VideoRequest
      • KlingTaskResponse
      • KlingTaskDetailResponse
      • KlingTaskListResponse
      • VeoGenerateRequest
      • VeoOperationResponse
      • VeoFetchOperationRequest
      • VeoFetchOperationResponse
  • V2
    • OpenAI
      • OpenAI response
      • OpenAI embeddings
      • OpenAI audio transcription
      • Chat completion (all text models)
      • OpenAI image generation
      • OpenAI image edit
      • OpenAI image edit (legacy alias)
    • Claude
      • Claude message
    • DeepSeek
      • DeepSeek chat completion
    • Gemini
      • Gemini content
    • Schemas
      • ChatCompletionRequest
      • ChatMessage
      • Tool
      • ToolCall
      • ChatCompletionResponse
      • ChatCompletionChoice
      • ContentFilterResults
      • UsageInfo
      • EmbeddingRequest
      • EmbeddingResponse
      • TranscriptionResponse
      • ClaudeMessageRequest
      • ClaudeMessageResponse
      • GeminiGenerateContentRequest
      • GeminiContent
      • GeminiGenerationConfig
      • GeminiGenerateContentResponse
      • ResponseRequest
      • ResponseObject
      • ImageGenerationRequest
      • ImageGenerationResponse
  1. OpenAI

OpenAI audio transcription

POST
https://ai.tikhub.io/v1/audio/transcriptions
OpenAI
Transcribes audio into the input language using the Whisper model. Supports various audio formats including mp3, mp4, mpeg, mpga, m4a, ogg, wav, and webm.

Supported Model#

whisper-1

Request

Authorization
Bearer Token
Provide your bearer token in the
Authorization
header when making requests to protected resources.
Example:
Authorization: Bearer ********************
or
Body Params multipart/form-dataRequired

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 'https://ai.tikhub.io/v1/audio/transcriptions' \
--header 'Authorization: Bearer <token>' \
--form 'file=@""' \
--form 'model=""' \
--form 'prompt=""' \
--form 'response_format="json"' \
--form 'temperature="0"' \
--form 'language=""' \
--form 'timestamp_granularities=""'

Responses

🟢200OK
application/json
Successful response
Body

Examples
{
    "task": "transcribe",
    "language": "en",
    "duration": 8.52,
    "text": "Hello everyone, welcome to the TikHub API demo. Today we will show how Whisper works.",
    "segments": [
        {
            "id": 0,
            "seek": 0,
            "start": 0,
            "end": 3.42,
            "text": "Hello everyone, welcome to the TikHub API demo.",
            "tokens": [
                50364,
                2425,
                1134,
                11,
                3037,
                281,
                264,
                2487,
                6815,
                4707,
                13,
                50514
            ],
            "temperature": 0,
            "avg_logprob": -0.21,
            "compression_ratio": 1.12,
            "no_speech_prob": 0.01,
            "words": [
                {
                    "word": "Hello",
                    "start": 0,
                    "end": 0.48
                },
                {
                    "word": "everyone,",
                    "start": 0.48,
                    "end": 1.12
                },
                {
                    "word": "welcome",
                    "start": 1.12,
                    "end": 1.78
                },
                {
                    "word": "to",
                    "start": 1.78,
                    "end": 1.95
                },
                {
                    "word": "the",
                    "start": 1.95,
                    "end": 2.12
                },
                {
                    "word": "TikHub",
                    "start": 2.12,
                    "end": 2.65
                },
                {
                    "word": "API",
                    "start": 2.65,
                    "end": 2.95
                },
                {
                    "word": "demo.",
                    "start": 2.95,
                    "end": 3.42
                }
            ]
        },
        {
            "id": 1,
            "seek": 342,
            "start": 3.42,
            "end": 8.52,
            "text": "Today we will show how Whisper works.",
            "tokens": [
                50514,
                4280,
                321,
                486,
                855,
                577,
                12355,
                1987,
                13,
                50764
            ],
            "temperature": 0,
            "avg_logprob": -0.18,
            "compression_ratio": 1.05,
            "no_speech_prob": 0,
            "words": [
                {
                    "word": "Today",
                    "start": 3.42,
                    "end": 3.88
                },
                {
                    "word": "we",
                    "start": 3.88,
                    "end": 4.05
                },
                {
                    "word": "will",
                    "start": 4.05,
                    "end": 4.32
                },
                {
                    "word": "show",
                    "start": 4.32,
                    "end": 4.78
                },
                {
                    "word": "how",
                    "start": 4.78,
                    "end": 5.02
                },
                {
                    "word": "Whisper",
                    "start": 5.02,
                    "end": 5.75
                },
                {
                    "word": "works.",
                    "start": 5.75,
                    "end": 6.42
                }
            ]
        }
    ]
}
🟠400Bad Request
🟠401Unauthorized
🟠429Too Many Requests
🔴500Internal Server Error
Modified at 2026-07-29 00:56:35
Previous
OpenAI embeddings
Next
DeepSeek chat completion
Built with