---
title: "Create transcription"
method: POST
path: "/1/ai/{product_id}/openai/audio/transcriptions"
tags: ["Usage > V1 > OpenAI-compatible"]
---

# Create transcription

`POST /1/ai/{product_id}/openai/audio/transcriptions`

Transcribes audio into the input language.
<br>
The input format is the same as OpenAI,
see the [OpenAI documentation](https://platform.openai.com/docs/api-reference/audio/createTranscription).
<br>
This route is asynchronous, use<br>
• [GET `/1/ai/{product_id}/results/{batch_id}`](/docs/api/get/1/ai/{product_id}/results/{batch_id}) to get the result<br>
• [GET `/1/ai/{product_id}/results/{batch_id}/download`](/docs/api/get/1/ai/{product_id}/results/{batch_id}/download) to download the output once done<br>

## Path parameters

- `product_id` integer, required

## Request body

- object
  - `append_punctuations` string — Only if timestamp_granularities[]:word is True, merge these punctuation symbols with the previous word
  - `chunk_length` integer — Defines the maximum duration for an active segment in sec. For subtitle tasks, it's recommended to set this to a short duration (5-10 seconds) to avoid long sentences.
  - `file` string, binary, required — The audio file to transcribe.<br>Its size must be less than *Max lengh* in kilobytes.<br>Allowed types: `mp3,mp4,aac,wav,flac,ogg,opus,wma,m4a,webm`.
  - `highlight_words` boolean — Subtitle task. Underline each word as it is spoken in srt and vtt output formats (requires timestamp_granularities[]:word)
  - `language` 'af' | 'am' | 'ar' | 'as' | 'az' | 'ba' | 'be' | 'bg' | 'bn' | 'bo' | 'br' | 'bs' | 'ca' | 'cs' | 'cy' | 'da' | 'de' | 'el' | 'en' | 'es' | 'et' | 'eu' | 'fa' | 'fi' | 'fo' | 'fr' | 'gl' | 'gu' | 'ha' | 'haw' | 'he' | 'hi' | 'hr' | 'ht' | 'hu' | 'hy' | 'id' | 'is' | 'it' | 'ja' | 'jw' | 'ka' | 'kk' | 'km' | 'kn' | 'ko' | 'la' | 'lb' | 'ln' | 'lo' | 'lt' | 'lv' | 'mg' | 'mi' | 'mk' | 'ml' | 'mn' | 'mr' | 'ms' | 'mt' | 'my' | 'ne' | 'nl' | 'nn' | 'no' | 'oc' | 'pa' | 'pl' | 'ps' | 'pt' | 'ro' | 'ru' | 'sa' | 'sd' | 'si' | 'sk' | 'sl' | 'sn' | 'so' | 'sq' | 'sr' | 'su' | 'sv' | 'sw' | 'ta' | 'te' | 'tg' | 'th' | 'tk' | 'tl' | 'tr' | 'tt' | 'uk' | 'ur' | 'uz' | 'vi' | 'yi' | 'yo' | 'yue' | 'zh' — The language of the input audio. Supplying the input language will translate the output.
  - `max_line_count` integer — Subtitle task. The maximum number of lines in a segment in srt and vtt output formats (requires timestamp_granularities[]:word)
  - `max_line_width` integer — Subtitle task. The maximum number of characters in a line before breaking the line in srt and vtt output formats (requires timestamp_granularities[]:word)
  - `max_words_per_line` integer — Subtitle task. The maximum number of words in a segment (requires timestamp_granularities[]:word)
  - `model` string, required — Model name to use
  - `no_speech_threshold` number, double — If the no_speech probability is higher than this value AND the average log probability over sampled tokens is below `log_prob_threshold`, consider the segment as silent.
  - `prepend_punctuations` string — Only if timestamp_granularities[]:word is True, merge these punctuation symbols with the next word
  - `prompt` string — An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
  - `response_format` 'json' | 'srt' | 'text' | 'verbose_json' | 'vtt' — The format of the transcript output (default: json)
  - `timestamp_granularities` string[] — The timestamp granularities to populate for this transcription. Either or both of these options are supported: word, or segment. Requires `response_format=verbose_json`. Defaults to segment.

## Response `200`

OK

- 4cee7ea0LlmSpeechToTextasyncmodeResponse — Represents a response returned by a model in async mode.
  - `batch_id` string, required — The id of the batch dispatched handling the transcription.

---

[API](https://skmtc.dev/infomaniak/apis/api-reference-developer-tools.md) · [All operations](https://skmtc.dev/infomaniak/apis/api-reference-developer-tools/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/infomaniak/api-reference-developer-tools/revisions/158a854b0c7d/schema)