--- title: "/v1/audio/transcriptions" method: POST path: "/v1/audio/transcriptions" tags: ["OpenAI ยท Audio"] --- # /v1/audio/transcriptions `POST /v1/audio/transcriptions` ## Request - Base URL: `https://aihubmix.com` - URL: `https://aihubmix.com/v1/audio/transcriptions` - Auth: HTTP bearer - TypeScript: (a function with typed inputs; its response is checked against the schema) Transcribes audio into the input language. Returns a transcription object in `json`, `diarized_json`, or `verbose_json` format, or a stream of transcript events. ## Request body `multipart/form-data` - CreateTranscriptionRequest - `file` string, binary, required: The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. - `model` union, required: ID of the model to use. The options are `gpt-transcribe`, `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`. - string - 'whisper-1' | 'gpt-transcribe' | 'gpt-4o-transcribe' | 'gpt-4o-mini-transcribe' | 'gpt-4o-mini-transcribe-2025-12-15' | 'gpt-4o-transcribe-diarize' - `language` string: 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. - `languages` string[]: Possible languages of the input audio, in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format. Supported by `gpt-transcribe`. - `keywords` string[]: Words or phrases to guide transcription of the input audio. Supported by `gpt-transcribe`. - `prompt` string: An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text#prompting) should match the audio language. This field is not supported when using `gpt-4o-transcribe-diarize`. - `response_format` 'json' | 'text' | 'srt' | 'verbose_json' | 'vtt' | 'diarized_json': 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. - `temperature` number: 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. - `include` TranscriptionInclude[]: 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`. - `timestamp_granularities` string[]: 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`. - `stream` boolean, nullable: 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](/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. - `chunking_strategy` union - 'auto': Automatically set chunking parameters based on the audio. Must be set to `"auto"`. - VadConfig - `type` 'server_vad', required: Must be set to `server_vad` to enable manual chunking using server side VAD. - `prefix_padding_ms` integer: Amount of audio to include before the VAD detected speech (in milliseconds). - `silence_duration_ms` integer: 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` number: 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. - `known_speaker_names` string[]: 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. - `known_speaker_references` string[]: 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`. ## Response `200` OK - union - CreateTranscriptionResponseJson: Represents a transcription response returned by model, based on the provided input. - `text` string, required: The transcribed text. - `languages` TranscriptionLanguage[]: The languages detected in the audio. Returned by `gpt-transcribe`. An empty array indicates that no language could be reliably detected. - `code` string, required: The code of a language detected in the audio. - `logprobs` object[]: 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. - `token` string: The token in the transcription. - `logprob` number: The log probability of the token. - `bytes` number[]: The bytes of the token. - `usage` union: Token usage statistics for the request. - object: Usage statistics for models billed by token usage. - `type` 'tokens', required: The type of the usage object. Always `tokens` for this variant. - `input_tokens` integer, required: Number of input tokens billed for this request. - `input_token_details` object: Details about the input tokens billed for this request. - `text_tokens` integer: Number of text tokens billed for this request. - `audio_tokens` integer: Number of audio tokens billed for this request. - `output_tokens` integer, required: Number of output tokens generated. - `total_tokens` integer, required: Total number of tokens used (input + output). - object: Usage statistics for models billed by audio input duration. - `type` 'duration', required: The type of the usage object. Always `duration` for this variant. - `seconds` number, double, required: Duration of the input audio in seconds. - CreateTranscriptionResponseDiarizedJson: Represents a diarized transcription response returned by the model, including the combined transcript and speaker-segment annotations. - `task` 'transcribe', required: The type of task that was run. Always `transcribe`. - `duration` number, double, required: Duration of the input audio in seconds. - `text` string, required: The concatenated transcript text for the entire audio input. - `segments` TranscriptionDiarizedSegment[], required: Segments of the transcript annotated with timestamps and speaker labels. - `type` 'transcript.text.segment', required: The type of the segment. Always `transcript.text.segment`. - `id` string, required: Unique identifier for the segment. - `start` number, double, required: Start timestamp of the segment in seconds. - `end` number, double, required: End timestamp of the segment in seconds. - `text` string, required: Transcript text for this segment. - `speaker` string, required: 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`, ...). - `usage` union: Token or duration usage statistics for the request. - object: Usage statistics for models billed by token usage. - `type` 'tokens', required: The type of the usage object. Always `tokens` for this variant. - `input_tokens` integer, required: Number of input tokens billed for this request. - `input_token_details` object: Details about the input tokens billed for this request. - `text_tokens` integer: Number of text tokens billed for this request. - `audio_tokens` integer: Number of audio tokens billed for this request. - `output_tokens` integer, required: Number of output tokens generated. - `total_tokens` integer, required: Total number of tokens used (input + output). - object: Usage statistics for models billed by audio input duration. - `type` 'duration', required: The type of the usage object. Always `duration` for this variant. - `seconds` number, double, required: Duration of the input audio in seconds. - CreateTranscriptionResponseVerboseJson: Represents a verbose json transcription response returned by model, based on the provided input. - `language` string, required: The language of the input audio. - `duration` number, double, required: The duration of the input audio. - `text` string, required: The transcribed text. - `words` TranscriptionWord[]: Extracted words and their corresponding timestamps. - `word` string, required: The text content of the word. - `start` number, double, required: Start time of the word in seconds. - `end` number, double, required: End time of the word in seconds. - `segments` TranscriptionSegment[]: Segments of the transcribed text and their corresponding details. - `id` integer, required: Unique identifier of the segment. - `seek` integer, required: Seek offset of the segment. - `start` number, double, required: Start time of the segment in seconds. - `end` number, double, required: End time of the segment in seconds. - `text` string, required: Text content of the segment. - `tokens` integer[], required: Array of token IDs for the text content. - `temperature` number, float, required: Temperature parameter used for generating the segment. - `avg_logprob` number, float, required: Average logprob of the segment. If the value is lower than -1, consider the logprobs failed. - `compression_ratio` number, float, required: Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed. - `no_speech_prob` number, float, required: 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. - `usage` TranscriptTextUsageDuration: Usage statistics for models billed by audio input duration. - `type` 'duration', required: The type of the usage object. Always `duration` for this variant. - `seconds` number, double, required: Duration of the input audio in seconds. ## Other responses - `400`: Invalid request - `401`: Authentication failed - `403`: Permission denied - `404`: Not found - `429`: Rate limited - `5XX`: Server / upstream error --- [API](https://skmtc.dev/inferera/apis/aihubmix-gateway-api.md) - [All operations](https://skmtc.dev/inferera/apis/aihubmix-gateway-api/llms.txt) - [OpenAPI document](https://skmtc.dev/inferera/apis/aihubmix-gateway-api/revisions/f293fe0500c2?raw)