> ## Documentation Index > Fetch the complete documentation index at: https://docs.aihubmix.com/llms.txt > Use this file to discover all available pages before exploring further. # Create Transcription > Transcribes audio into the input language. Returns a transcription object in `json`, `diarized_json`, or `verbose_json` format, or a stream of transcript events. ## OpenAPI ````yaml /openapi.json post /v1/audio/transcriptions openapi: 3.1.0 info: title: AIHubMix Gateway API description: | Unified multi-protocol gateway. Exposes three native shapes side-by-side: - OpenAI (`/v1/chat/completions`, `/v1/responses`, ...) - Anthropic (`/v1/messages`) - Gemini (`/v1beta/models/{model}:generateContent`) Each vendor's native SDK connects directly. Gateway-only fields are marked with `x-source.authority: gateway`. contact: name: AIHubMix Team version: 2.1.1 x-upstream: vendorSpecs: packageVersion: 0.1.1 installedFrom: npm sources: openai/official: version: '2026-05-31' hash: >- sha256:a203971a0bc0cd3b903b9488e3ac40eaa161a274dfaf172c1da73eee029147a8 anthropic/official: version: '2026-05-31' hash: >- sha256:f9d488f9290d78a081bed62fa0c040476b5d009f3db92c06c8e279e69df73fc9 layers: - role: L0-base source: avs://openai/official protocol: openai authority: official - role: L0-base source: avs://anthropic/official protocol: anthropic authority: official - role: gateway-other source: gateway/anthropic-mappings.yml protocol: all authority: gateway - role: horizontal-auth source: gateway/auth.yml protocol: all authority: gateway - role: horizontal-errors source: gateway/errors.yml protocol: all authority: gateway - role: L3-gateway source: gateway/openai-gateway.yml protocol: openai authority: gateway - role: gateway-other source: gateway/openai-image-mappings.yml protocol: all authority: gateway - role: gateway-other source: gateway/openai-mappings.yml protocol: all authority: gateway - role: L2-passthrough source: gateway/openai-passthrough.yml protocol: openai authority: gateway servers: - url: https://aihubmix.com description: Production - url: https://api.inferera.com description: Backup (use when the primary domain is unreachable) security: - gatewayBearer: [] tags: - name: OpenAI Compatible description: >- OpenAI-compatible endpoints (chat, completions, embeddings, images, audio, videos, moderations). - name: Anthropic Compatible description: Anthropic-native endpoints (messages with Anthropic protocol). - name: Google Vertex AI Compatible description: Google Gemini / Vertex AI endpoints. paths: /v1/audio/transcriptions: post: tags: - OpenAI Compatible summary: Create Transcription description: >- Transcribes audio into the input language. Returns a transcription object in `json`, `diarized_json`, or `verbose_json` format, or a stream of transcript events. operationId: createTranscription requestBody: required: true content: multipart/form-data: schema: $ref: '#/components/schemas/CreateTranscriptionRequest' responses: '200': description: OK content: application/json: schema: oneOf: - $ref: '#/components/schemas/CreateTranscriptionResponseJson' - $ref: >- #/components/schemas/CreateTranscriptionResponseDiarizedJson - $ref: >- #/components/schemas/CreateTranscriptionResponseVerboseJson text/event-stream: schema: $ref: '#/components/schemas/CreateTranscriptionResponseStreamEvent' '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/GatewayError' '401': description: Authentication failed content: application/json: schema: $ref: '#/components/schemas/GatewayError' '403': description: Permission denied content: application/json: schema: $ref: '#/components/schemas/GatewayError' '404': description: Not found content: application/json: schema: $ref: '#/components/schemas/GatewayError' '429': description: Rate limited content: application/json: schema: $ref: '#/components/schemas/GatewayError' 5XX: description: Server / upstream error content: application/json: schema: $ref: '#/components/schemas/GatewayError' components: schemas: CreateTranscriptionRequest: type: object additionalProperties: false properties: file: description: > The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. type: string format: binary model: description: > ID of the model to use. The options are `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1` (which is powered by our open source Whisper V2 model), and `gpt-4o-transcribe-diarize`. example: gpt-4o-transcribe anyOf: - type: string - type: string enum: - whisper-1 - gpt-4o-transcribe - gpt-4o-mini-transcribe - gpt-4o-mini-transcribe-2025-12-15 - gpt-4o-transcribe-diarize language: description: > The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format will improve accuracy and latency. type: string prompt: description: > An optional text to guide the model's style or continue a previous audio segment. The [prompt](https://developers.openai.com/api/docs/guides/speech-to-text#prompting) should match the audio language. This field is not supported when using `gpt-4o-transcribe-diarize`. type: string response_format: $ref: '#/components/schemas/AudioResponseFormat' temperature: description: > The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. type: number default: 0 include: description: > Additional information to include in the transcription response. `logprobs` will return the log probabilities of the tokens in the response to understand the model's confidence in the transcription. `logprobs` only works with response_format set to `json` and only with the models `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is not supported when using `gpt-4o-transcribe-diarize`. type: array items: $ref: '#/components/schemas/TranscriptionInclude' timestamp_granularities: description: > The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency. This option is not available for `gpt-4o-transcribe-diarize`. type: array items: type: string enum: - word - segment default: - segment stream: anyOf: - description: > If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section of the Speech-to-Text guide](https://developers.openai.com/api/docs/guides/speech-to-text?lang=curl#streaming-transcriptions) for more information. Note: Streaming is not supported for the `whisper-1` model and will be ignored. type: boolean default: false - type: 'null' chunking_strategy: anyOf: - description: >- Controls how the audio is cut into chunks. When set to `"auto"`, the server first normalizes loudness and then uses voice activity detection (VAD) to choose boundaries. `server_vad` object can be provided to tweak VAD detection parameters manually. If unset, the audio is transcribed as a single block. Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30 seconds. anyOf: - type: string enum: - auto default: auto description: > Automatically set chunking parameters based on the audio. Must be set to `"auto"`. - $ref: '#/components/schemas/VadConfig' - type: 'null' known_speaker_names: description: > Optional list of speaker names that correspond to the audio samples provided in `known_speaker_references[]`. Each entry should be a short identifier (for example `customer` or `agent`). Up to 4 speakers are supported. type: array maxItems: 4 items: type: string known_speaker_references: description: > Optional list of audio samples (as [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs)) that contain known speaker references matching `known_speaker_names[]`. Each sample must be between 2 and 10 seconds, and can use any of the same input audio formats supported by `file`. type: array maxItems: 4 items: type: string required: - file - model x-source: from: avs://openai/official authority: official CreateTranscriptionResponseJson: type: object description: >- Represents a transcription response returned by model, based on the provided input. properties: text: type: string description: The transcribed text. logprobs: type: array optional: true description: > The log probabilities of the tokens in the transcription. Only returned with the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe` if `logprobs` is added to the `include` array. items: type: object properties: token: type: string description: The token in the transcription. logprob: type: number description: The log probability of the token. bytes: type: array items: type: number description: The bytes of the token. usage: description: Token usage statistics for the request. oneOf: - $ref: '#/components/schemas/TranscriptTextUsageTokens' title: Token Usage - $ref: '#/components/schemas/TranscriptTextUsageDuration' title: Duration Usage required: - text x-source: from: avs://openai/official authority: official CreateTranscriptionResponseDiarizedJson: type: object description: > Represents a diarized transcription response returned by the model, including the combined transcript and speaker-segment annotations. properties: task: type: string description: The type of task that was run. Always `transcribe`. enum: - transcribe duration: type: number format: double description: Duration of the input audio in seconds. text: type: string description: The concatenated transcript text for the entire audio input. segments: type: array description: >- Segments of the transcript annotated with timestamps and speaker labels. items: $ref: '#/components/schemas/TranscriptionDiarizedSegment' usage: description: Token or duration usage statistics for the request. oneOf: - $ref: '#/components/schemas/TranscriptTextUsageTokens' title: Token Usage - $ref: '#/components/schemas/TranscriptTextUsageDuration' title: Duration Usage discriminator: propertyName: type required: - task - duration - text - segments x-source: from: avs://openai/official authority: official CreateTranscriptionResponseVerboseJson: type: object description: >- Represents a verbose json transcription response returned by model, based on the provided input. properties: language: type: string description: The language of the input audio. duration: type: number format: double description: The duration of the input audio. text: type: string description: The transcribed text. words: type: array description: Extracted words and their corresponding timestamps. items: $ref: '#/components/schemas/TranscriptionWord' segments: type: array description: Segments of the transcribed text and their corresponding details. items: $ref: '#/components/schemas/TranscriptionSegment' usage: $ref: '#/components/schemas/TranscriptTextUsageDuration' required: - language - duration - text x-source: from: avs://openai/official authority: official CreateTranscriptionResponseStreamEvent: anyOf: - $ref: '#/components/schemas/TranscriptTextSegmentEvent' - $ref: '#/components/schemas/TranscriptTextDeltaEvent' - $ref: '#/components/schemas/TranscriptTextDoneEvent' discriminator: propertyName: type x-source: from: avs://openai/official authority: official GatewayError: type: object description: | OpenAI-compatible error envelope. Top-level `error` object carrying `message` / `type` / `param` / `code`. `request_id` lives in the `X-Request-Id` response header, not in the body. The legacy `upstream` field is no longer emitted. x-source: from: gateway authority: gateway required: - error properties: error: type: object required: - message properties: message: type: string description: Human-readable error message. type: type: string nullable: true description: > Error category. OpenAI-compatible values include invalid_request_error / authentication_error / permission_error / not_found_error / rate_limit_error, etc. The upstream value is passed through verbatim; the enum is not fixed. param: type: string nullable: true description: Name of the offending field, when applicable. code: nullable: true description: | Sub-error code. May be a string or integer (the gateway treats `code` as an arbitrary type). AudioResponseFormat: description: > The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, `vtt`, or `diarized_json`. For `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`, the only supported format is `json`. For `gpt-4o-transcribe-diarize`, the supported formats are `json`, `text`, and `diarized_json`, with `diarized_json` required to receive speaker annotations. type: string enum: - json - text - srt - verbose_json - vtt - diarized_json default: json x-source: from: avs://openai/official authority: official TranscriptionInclude: type: string enum: - logprobs default: [] x-source: from: avs://openai/official authority: official VadConfig: type: object additionalProperties: false required: - type properties: type: type: string enum: - server_vad description: >- Must be set to `server_vad` to enable manual chunking using server side VAD. prefix_padding_ms: type: integer default: 300 description: | Amount of audio to include before the VAD detected speech (in milliseconds). silence_duration_ms: type: integer default: 200 description: | Duration of silence to detect speech stop (in milliseconds). With shorter values the model will respond more quickly, but may jump in on short pauses from the user. threshold: type: number default: 0.5 description: > Sensitivity threshold (0.0 to 1.0) for voice activity detection. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments. x-source: from: avs://openai/official authority: official TranscriptTextUsageTokens: type: object title: Token Usage description: Usage statistics for models billed by token usage. properties: type: type: string enum: - tokens description: The type of the usage object. Always `tokens` for this variant. input_tokens: type: integer description: Number of input tokens billed for this request. input_token_details: type: object description: Details about the input tokens billed for this request. properties: text_tokens: type: integer description: Number of text tokens billed for this request. audio_tokens: type: integer description: Number of audio tokens billed for this request. output_tokens: type: integer description: Number of output tokens generated. total_tokens: type: integer description: Total number of tokens used (input + output). required: - type - input_tokens - output_tokens - total_tokens x-source: from: avs://openai/official authority: official TranscriptTextUsageDuration: type: object title: Duration Usage description: Usage statistics for models billed by audio input duration. properties: type: type: string enum: - duration description: The type of the usage object. Always `duration` for this variant. seconds: type: number format: double description: Duration of the input audio in seconds. required: - type - seconds x-source: from: avs://openai/official authority: official TranscriptionDiarizedSegment: type: object description: A segment of diarized transcript text with speaker metadata. properties: type: type: string description: | The type of the segment. Always `transcript.text.segment`. enum: - transcript.text.segment id: type: string description: Unique identifier for the segment. start: type: number format: double description: Start timestamp of the segment in seconds. end: type: number format: double description: End timestamp of the segment in seconds. text: type: string description: Transcript text for this segment. speaker: type: string description: > Speaker label for this segment. When known speakers are provided, the label matches `known_speaker_names[]`. Otherwise speakers are labeled sequentially using capital letters (`A`, `B`, ...). required: - type - id - start - end - text - speaker x-source: from: avs://openai/official authority: official TranscriptionWord: type: object properties: word: type: string description: The text content of the word. start: type: number format: double description: Start time of the word in seconds. end: type: number format: double description: End time of the word in seconds. required: - word - start - end x-source: from: avs://openai/official authority: official TranscriptionSegment: type: object properties: id: type: integer description: Unique identifier of the segment. seek: type: integer description: Seek offset of the segment. start: type: number format: double description: Start time of the segment in seconds. end: type: number format: double description: End time of the segment in seconds. text: type: string description: Text content of the segment. tokens: type: array items: type: integer description: Array of token IDs for the text content. temperature: type: number format: float description: Temperature parameter used for generating the segment. avg_logprob: type: number format: float description: >- Average logprob of the segment. If the value is lower than -1, consider the logprobs failed. compression_ratio: type: number format: float description: >- Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed. no_speech_prob: type: number format: float description: >- Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent. required: - id - seek - start - end - text - tokens - temperature - avg_logprob - compression_ratio - no_speech_prob x-source: from: avs://openai/official authority: official TranscriptTextSegmentEvent: type: object description: > Emitted when a diarized transcription returns a completed segment with speaker information. Only emitted when you [create a transcription](https://developers.openai.com/api/docs/api-reference/audio/create-transcription) with `stream` set to `true` and `response_format` set to `diarized_json`. properties: type: type: string description: The type of the event. Always `transcript.text.segment`. enum: - transcript.text.segment id: type: string description: Unique identifier for the segment. start: type: number format: double description: Start timestamp of the segment in seconds. end: type: number format: double description: End timestamp of the segment in seconds. text: type: string description: Transcript text for this segment. speaker: type: string description: Speaker label for this segment. required: - type - id - start - end - text - speaker x-source: from: avs://openai/official authority: official TranscriptTextDeltaEvent: type: object description: >- Emitted when there is an additional text delta. This is also the first event emitted when the transcription starts. Only emitted when you [create a transcription](https://developers.openai.com/api/docs/api-reference/audio/create-transcription) with the `Stream` parameter set to `true`. properties: type: type: string description: | The type of the event. Always `transcript.text.delta`. enum: - transcript.text.delta delta: type: string description: | The text delta that was additionally transcribed. logprobs: type: array description: > The log probabilities of the delta. Only included if you [create a transcription](https://developers.openai.com/api/docs/api-reference/audio/create-transcription) with the `include[]` parameter set to `logprobs`. items: type: object properties: token: type: string description: | The token that was used to generate the log probability. logprob: type: number description: | The log probability of the token. bytes: type: array items: type: integer description: | The bytes that were used to generate the log probability. segment_id: type: string description: > Identifier of the diarized segment that this delta belongs to. Only present when using `gpt-4o-transcribe-diarize`. required: - type - delta x-source: from: avs://openai/official authority: official TranscriptTextDoneEvent: type: object description: >- Emitted when the transcription is complete. Contains the complete transcription text. Only emitted when you [create a transcription](https://developers.openai.com/api/docs/api-reference/audio/create-transcription) with the `Stream` parameter set to `true`. properties: type: type: string description: | The type of the event. Always `transcript.text.done`. enum: - transcript.text.done text: type: string description: | The text that was transcribed. logprobs: type: array description: > The log probabilities of the individual tokens in the transcription. Only included if you [create a transcription](https://developers.openai.com/api/docs/api-reference/audio/create-transcription) with the `include[]` parameter set to `logprobs`. items: type: object properties: token: type: string description: | The token that was used to generate the log probability. logprob: type: number description: | The log probability of the token. bytes: type: array items: type: integer description: | The bytes that were used to generate the log probability. usage: $ref: '#/components/schemas/TranscriptTextUsageTokens' required: - type - text x-source: from: avs://openai/official authority: official securitySchemes: gatewayBearer: type: http scheme: bearer bearerFormat: API Key description: | Gateway-issued API key, formatted as `sk-gateway-xxxxxxxx`. Used by OpenAI-shaped endpoints (/v1/chat/completions, etc.). x-source: from: gateway authority: gateway ````