Skip to content

Create transcription

client.Audio.Transcriptions.New(ctx, body) (*AudioTranscriptionNewResponseUnion, error)
POST/audio/transcriptions

Transcribes audio into the input language.

ParametersExpand Collapse
body AudioTranscriptionNewParams
File param.Field[Reader]

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 param.Field[AudioModel]

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.

string
type AudioModel string
Accepts one of the following:
const AudioModelWhisper1 AudioModel = "whisper-1"
const AudioModelGPT4oTranscribe AudioModel = "gpt-4o-transcribe"
const AudioModelGPT4oMiniTranscribe AudioModel = "gpt-4o-mini-transcribe"
const AudioModelGPT4oMiniTranscribe2025_12_15 AudioModel = "gpt-4o-mini-transcribe-2025-12-15"
const AudioModelGPT4oTranscribeDiarize AudioModel = "gpt-4o-transcribe-diarize"
ChunkingStrategy param.Field[AudioTranscriptionNewParamsChunkingStrategyUnion]optional

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.

Auto
AudioTranscriptionNewParamsChunkingStrategyVadConfig
Type string

Must be set to server_vad to enable manual chunking using server side VAD.

PrefixPaddingMs int64optional

Amount of audio to include before the VAD detected speech (in milliseconds).

SilenceDurationMs int64optional

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 float64optional

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.

Include param.Field[[]TranscriptionInclude]optional

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.

const TranscriptionIncludeLogprobs TranscriptionInclude = "logprobs"
KnownSpeakerNames param.Field[[]string]optional

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.

KnownSpeakerReferences param.Field[[]string]optional

Optional list of audio samples (as 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.

Language param.Field[string]optional

The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.

Prompt param.Field[string]optional

An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language. This field is not supported when using gpt-4o-transcribe-diarize.

ResponseFormat param.Field[AudioResponseFormat]optional

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 param.Field[float64]optional

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 to automatically increase the temperature until certain thresholds are hit.

TimestampGranularities param.Field[[]string]optional

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.

const AudioTranscriptionNewParamsTimestampGranularityWord AudioTranscriptionNewParamsTimestampGranularity = "word"
const AudioTranscriptionNewParamsTimestampGranularitySegment AudioTranscriptionNewParamsTimestampGranularity = "segment"
ReturnsExpand Collapse
type AudioTranscriptionNewResponseUnion interface{…}

Represents a transcription response returned by model, based on the provided input.

Accepts one of the following:
type Transcription struct{…}

Represents a transcription response returned by model, based on the provided input.

Text string

The transcribed text.

Logprobs []TranscriptionLogproboptional

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 stringoptional

The token in the transcription.

Bytes []float64optional

The bytes of the token.

Logprob float64optional

The log probability of the token.

Usage TranscriptionUsageUnionoptional

Token usage statistics for the request.

Accepts one of the following:
type TranscriptionUsageTokens struct{…}

Usage statistics for models billed by token usage.

InputTokens int64

Number of input tokens billed for this request.

OutputTokens int64

Number of output tokens generated.

TotalTokens int64

Total number of tokens used (input + output).

Type Tokens

The type of the usage object. Always tokens for this variant.

InputTokenDetails TranscriptionUsageTokensInputTokenDetailsoptional

Details about the input tokens billed for this request.

AudioTokens int64optional

Number of audio tokens billed for this request.

TextTokens int64optional

Number of text tokens billed for this request.

type TranscriptionUsageDuration struct{…}

Usage statistics for models billed by audio input duration.

Seconds float64

Duration of the input audio in seconds.

Type Duration

The type of the usage object. Always duration for this variant.

type TranscriptionVerbose struct{…}

Represents a verbose json transcription response returned by model, based on the provided input.

Duration float64

The duration of the input audio.

Language string

The language of the input audio.

Text string

The transcribed text.

Segments []TranscriptionSegmentoptional

Segments of the transcribed text and their corresponding details.

ID int64

Unique identifier of the segment.

AvgLogprob float64

Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.

formatfloat
CompressionRatio float64

Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.

formatfloat
End float64

End time of the segment in seconds.

formatfloat
NoSpeechProb float64

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.

formatfloat
Seek int64

Seek offset of the segment.

Start float64

Start time of the segment in seconds.

formatfloat
Temperature float64

Temperature parameter used for generating the segment.

formatfloat
Text string

Text content of the segment.

Tokens []int64

Array of token IDs for the text content.

Usage TranscriptionVerboseUsageoptional

Usage statistics for models billed by audio input duration.

Seconds float64

Duration of the input audio in seconds.

Type Duration

The type of the usage object. Always duration for this variant.

Words []TranscriptionWordoptional

Extracted words and their corresponding timestamps.

End float64

End time of the word in seconds.

formatfloat
Start float64

Start time of the word in seconds.

formatfloat
Word string

The text content of the word.

type TranscriptionStreamEventUnion interface{…}

Emitted when a diarized transcription returns a completed segment with speaker information. Only emitted when you create a transcription with stream set to true and response_format set to diarized_json.

Accepts one of the following:
type TranscriptionTextSegmentEvent struct{…}

Emitted when a diarized transcription returns a completed segment with speaker information. Only emitted when you create a transcription with stream set to true and response_format set to diarized_json.

ID string

Unique identifier for the segment.

End float64

End timestamp of the segment in seconds.

formatfloat
Speaker string

Speaker label for this segment.

Start float64

Start timestamp of the segment in seconds.

formatfloat
Text string

Transcript text for this segment.

Type TranscriptTextSegment

The type of the event. Always transcript.text.segment.

type TranscriptionTextDeltaEvent struct{…}

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 with the Stream parameter set to true.

Delta string

The text delta that was additionally transcribed.

Type TranscriptTextDelta

The type of the event. Always transcript.text.delta.

Logprobs []TranscriptionTextDeltaEventLogproboptional

The log probabilities of the delta. Only included if you create a transcription with the include[] parameter set to logprobs.

Token stringoptional

The token that was used to generate the log probability.

Bytes []int64optional

The bytes that were used to generate the log probability.

Logprob float64optional

The log probability of the token.

SegmentID stringoptional

Identifier of the diarized segment that this delta belongs to. Only present when using gpt-4o-transcribe-diarize.

type TranscriptionTextDoneEvent struct{…}

Emitted when the transcription is complete. Contains the complete transcription text. Only emitted when you create a transcription with the Stream parameter set to true.

Text string

The text that was transcribed.

Type TranscriptTextDone

The type of the event. Always transcript.text.done.

Logprobs []TranscriptionTextDoneEventLogproboptional

The log probabilities of the individual tokens in the transcription. Only included if you create a transcription with the include[] parameter set to logprobs.

Token stringoptional

The token that was used to generate the log probability.

Bytes []int64optional

The bytes that were used to generate the log probability.

Logprob float64optional

The log probability of the token.

Usage TranscriptionTextDoneEventUsageoptional

Usage statistics for models billed by token usage.

InputTokens int64

Number of input tokens billed for this request.

OutputTokens int64

Number of output tokens generated.

TotalTokens int64

Total number of tokens used (input + output).

Type Tokens

The type of the usage object. Always tokens for this variant.

InputTokenDetails TranscriptionTextDoneEventUsageInputTokenDetailsoptional

Details about the input tokens billed for this request.

AudioTokens int64optional

Number of audio tokens billed for this request.

TextTokens int64optional

Number of text tokens billed for this request.

Create transcription

package main

import (
  "bytes"
  "context"
  "fmt"
  "io"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  transcription, err := client.Audio.Transcriptions.New(context.TODO(), openai.AudioTranscriptionNewParams{
    File: io.Reader(bytes.NewBuffer([]byte("some file contents"))),
    Model: openai.AudioModelGPT4oTranscribe,
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", transcription)
}
{
  "text": "text",
  "logprobs": [
    {
      "token": "token",
      "bytes": [
        0
      ],
      "logprob": 0
    }
  ],
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0,
    "total_tokens": 0,
    "type": "tokens",
    "input_token_details": {
      "audio_tokens": 0,
      "text_tokens": 0
    }
  }
}
Returns Examples
{
  "text": "text",
  "logprobs": [
    {
      "token": "token",
      "bytes": [
        0
      ],
      "logprob": 0
    }
  ],
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0,
    "total_tokens": 0,
    "type": "tokens",
    "input_token_details": {
      "audio_tokens": 0,
      "text_tokens": 0
    }
  }
}