Create transcription
Transcribes audio into the input language.
ParametersExpand Collapse
TranscriptionCreateParams params
The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
AudioModel modelID 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.
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.
Optional<ChunkingStrategy> chunkingStrategyControls 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.
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.
class VadConfig:
Must be set to server_vad to enable manual chunking using server side VAD.
Amount of audio to include before the VAD detected speech (in milliseconds).
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.
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.
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.
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.
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.
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.
The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.
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.
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.
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.
Optional<List<TimestampGranularity>> timestampGranularitiesThe 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.
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.
ReturnsExpand Collapse
class TranscriptionCreateResponse: A class that can be one of several variants.union Represents a transcription response returned by model, based on the provided input.
Represents a transcription response returned by model, based on the provided input.
class Transcription:Represents a transcription response returned by model, based on the provided input.
Represents a transcription response returned by model, based on the provided input.
The transcribed text.
Optional<List<Logprob>> logprobsThe 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.
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.
The token in the transcription.
The bytes of the token.
The log probability of the token.
Optional<Usage> usageToken usage statistics for the request.
Token usage statistics for the request.
class Tokens:Usage statistics for models billed by token usage.
Usage statistics for models billed by token usage.
Number of input tokens billed for this request.
Number of output tokens generated.
Total number of tokens used (input + output).
The type of the usage object. Always tokens for this variant.
Optional<InputTokenDetails> inputTokenDetailsDetails about the input tokens billed for this request.
Details about the input tokens billed for this request.
Number of audio tokens billed for this request.
Number of text tokens billed for this request.
class Duration:Usage statistics for models billed by audio input duration.
Usage statistics for models billed by audio input duration.
Duration of the input audio in seconds.
The type of the usage object. Always duration for this variant.
class TranscriptionDiarized:Represents a diarized transcription response returned by the model, including the combined transcript and speaker-segment annotations.
Represents a diarized transcription response returned by the model, including the combined transcript and speaker-segment annotations.
Duration of the input audio in seconds.
List<TranscriptionDiarizedSegment> segmentsSegments of the transcript annotated with timestamps and speaker labels.
Segments of the transcript annotated with timestamps and speaker labels.
Unique identifier for the segment.
End timestamp of the segment in seconds.
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, ...).
Start timestamp of the segment in seconds.
Transcript text for this segment.
The type of the segment. Always transcript.text.segment.
The type of task that was run. Always transcribe.
The concatenated transcript text for the entire audio input.
Optional<Usage> usageToken or duration usage statistics for the request.
Token or duration usage statistics for the request.
class Tokens:Usage statistics for models billed by token usage.
Usage statistics for models billed by token usage.
Number of input tokens billed for this request.
Number of output tokens generated.
Total number of tokens used (input + output).
The type of the usage object. Always tokens for this variant.
Optional<InputTokenDetails> inputTokenDetailsDetails about the input tokens billed for this request.
Details about the input tokens billed for this request.
Number of audio tokens billed for this request.
Number of text tokens billed for this request.
class Duration:Usage statistics for models billed by audio input duration.
Usage statistics for models billed by audio input duration.
Duration of the input audio in seconds.
The type of the usage object. Always duration for this variant.
class TranscriptionVerbose:Represents a verbose json transcription response returned by model, based on the provided input.
Represents a verbose json transcription response returned by model, based on the provided input.
The duration of the input audio.
The language of the input audio.
The transcribed text.
Segments of the transcribed text and their corresponding details.
Segments of the transcribed text and their corresponding details.
Unique identifier of the segment.
Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
End time of the segment in seconds.
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.
Seek offset of the segment.
Start time of the segment in seconds.
Temperature parameter used for generating the segment.
Text content of the segment.
Array of token IDs for the text content.
Optional<Usage> usageUsage statistics for models billed by audio input duration.
Usage statistics for models billed by audio input duration.
Duration of the input audio in seconds.
The type of the usage object. Always duration for this variant.
Extracted words and their corresponding timestamps.
Extracted words and their corresponding timestamps.
End time of the word in seconds.
Start time of the word in seconds.
The text content of the word.
class TranscriptionStreamEvent: A class that can be one of several variants.union 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.
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.
class TranscriptionTextSegmentEvent: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.
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.
Unique identifier for the segment.
End timestamp of the segment in seconds.
Speaker label for this segment.
Start timestamp of the segment in seconds.
Transcript text for this segment.
The type of the event. Always transcript.text.segment.
class TranscriptionTextDeltaEvent: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.
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.
The text delta that was additionally transcribed.
The type of the event. Always transcript.text.delta.
Optional<List<Logprob>> logprobsThe log probabilities of the delta. Only included if you create a transcription with the include[] parameter set to logprobs.
The log probabilities of the delta. Only included if you create a transcription with the include[] parameter set to logprobs.
The token that was used to generate the log probability.
The bytes that were used to generate the log probability.
The log probability of the token.
Identifier of the diarized segment that this delta belongs to. Only present when using gpt-4o-transcribe-diarize.
class TranscriptionTextDoneEvent: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.
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.
The text that was transcribed.
The type of the event. Always transcript.text.done.
Optional<List<Logprob>> logprobsThe log probabilities of the individual tokens in the transcription. Only included if you create a transcription with the include[] parameter set to logprobs.
The log probabilities of the individual tokens in the transcription. Only included if you create a transcription with the include[] parameter set to logprobs.
The token that was used to generate the log probability.
The bytes that were used to generate the log probability.
The log probability of the token.
Optional<Usage> usageUsage statistics for models billed by token usage.
Usage statistics for models billed by token usage.
Number of input tokens billed for this request.
Number of output tokens generated.
Total number of tokens used (input + output).
The type of the usage object. Always tokens for this variant.
Optional<InputTokenDetails> inputTokenDetailsDetails about the input tokens billed for this request.
Details about the input tokens billed for this request.
Number of audio tokens billed for this request.
Number of text tokens billed for this request.
Create transcription
package com.openai.example;
import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.audio.AudioModel;
import com.openai.models.audio.transcriptions.TranscriptionCreateParams;
import com.openai.models.audio.transcriptions.TranscriptionCreateResponse;
import java.io.ByteArrayInputStream;
public final class Main {
private Main() {}
public static void main(String[] args) {
OpenAIClient client = OpenAIOkHttpClient.fromEnv();
TranscriptionCreateParams params = TranscriptionCreateParams.builder()
.file(ByteArrayInputStream("some content".getBytes()))
.model(AudioModel.GPT_4O_TRANSCRIBE)
.build();
TranscriptionCreateResponse transcription = client.audio().transcriptions().create(params);
}
}{
"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
}
}
}