> ## Documentation Index > Fetch the complete documentation index at: https://developers.telnyx.com/llms.txt > Use this file to discover all available pages before exploring further. # Transcribe speech to text > Transcribe speech to text. This endpoint is consistent with the [OpenAI Transcription API](https://platform.openai.com/docs/api-reference/audio/createTranscription) and may be used with the OpenAI JS or Python SDK. ## OpenAPI ````yaml https://telnyx-openapi-ng.s3.us-east-1.amazonaws.com/speech-to-text-filebased/speech-to-text-filebased.yml post /ai/audio/transcriptions openapi: 3.1.0 info: title: Speech to Text File Based API version: 2.0.0 description: API for managing Speech to Text File Based. contact: email: support@telnyx.com servers: - url: https://api.telnyx.com/v2 security: - bearerAuth: [] tags: - name: Speech to Text File Based description: Speech to Text File Based operations paths: /ai/audio/transcriptions: post: tags: - Audio summary: Transcribe speech to text description: >- Transcribe speech to text. This endpoint is consistent with the [OpenAI Transcription API](https://platform.openai.com/docs/api-reference/audio/createTranscription) and may be used with the OpenAI JS or Python SDK. operationId: audio_public_audio_transcriptions_post requestBody: required: true content: multipart/form-data: schema: $ref: '#/components/schemas/AudioTranscriptionRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AudioTranscriptionResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-codeSamples: - lang: JavaScript source: >- import fs from 'fs'; import Telnyx from 'telnyx'; const client = new Telnyx({ apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted }); const response = await client.ai.audio.transcribe({ model: 'distil-whisper/distil-large-v2' }); console.log(response.text); - lang: Python source: |- import os from telnyx import Telnyx client = Telnyx( api_key=os.environ.get("TELNYX_API_KEY"), # This is the default and can be omitted ) response = client.ai.audio.transcribe( model="distil-whisper/distil-large-v2", ) print(response.text) - lang: Go source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\n\t\"github.com/team-telnyx/telnyx-go\"\n\t\"github.com/team-telnyx/telnyx-go/option\"\n)\n\nfunc main() {\n\tclient := telnyx.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\tresponse, err := client.AI.Audio.Transcribe(context.TODO(), telnyx.AIAudioTranscribeParams{\n\t\tModel: telnyx.AIAudioTranscribeParamsModelDistilWhisperDistilLargeV2,\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", response.Text)\n}\n" - lang: Java source: |- package com.telnyx.sdk.example; import com.telnyx.sdk.client.TelnyxClient; import com.telnyx.sdk.client.okhttp.TelnyxOkHttpClient; import com.telnyx.sdk.models.ai.audio.AudioTranscribeParams; import com.telnyx.sdk.models.ai.audio.AudioTranscribeResponse; public final class Main { private Main() {} public static void main(String[] args) { TelnyxClient client = TelnyxOkHttpClient.fromEnv(); AudioTranscribeParams params = AudioTranscribeParams.builder() .model(AudioTranscribeParams.Model.DISTIL_WHISPER_DISTIL_LARGE_V2) .build(); AudioTranscribeResponse response = client.ai().audio().transcribe(params); } } - lang: Ruby source: >- require "telnyx" telnyx = Telnyx::Client.new(api_key: "My API Key") response = telnyx.ai.audio.transcribe(model: :"distil-whisper/distil-large-v2") puts(response) - lang: CLI source: |- telnyx ai:audio transcribe \ --api-key 'My API Key' \ --model distil-whisper/distil-large-v2 components: schemas: AudioTranscriptionRequest: type: object properties: file: description: >- The audio file object to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. File uploads are limited to 100 MB. Cannot be used together with `file_url`. Note: `deepgram/nova-3` only supports mp3 and wav formats. type: string format: binary file_url: description: >- Link to audio file in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. Support for hosted files is limited to 100MB. Cannot be used together with `file`. Note: `deepgram/nova-3` only supports mp3 and wav formats. type: string example: https://example.com/file.mp3 model: description: >- ID of the model to use. `distil-whisper/distil-large-v2` is lower latency but English-only. `openai/whisper-large-v3-turbo` is multi-lingual but slightly higher latency. `deepgram/nova-3` supports English variants (en, en-US, en-GB, en-AU, en-NZ, en-IN) and only accepts mp3/wav files. example: distil-whisper/distil-large-v2 default: distil-whisper/distil-large-v2 type: string enum: - distil-whisper/distil-large-v2 - openai/whisper-large-v3-turbo - deepgram/nova-3 response_format: description: >- The format of the transcript output. Use `verbose_json` to take advantage of timestamps. example: json type: string default: json enum: - json - verbose_json timestamp_granularities[]: description: >- The timestamp granularities to populate for this transcription. `response_format` must be set verbose_json to use timestamp granularities. Currently `segment` is supported. example: segment type: string enum: - segment language: type: string description: >- The language of the audio to be transcribed. For `deepgram/nova-3`, only English variants are supported: `en`, `en-US`, `en-GB`, `en-AU`, `en-NZ`, `en-IN`. For `openai/whisper-large-v3-turbo`, supports multiple languages. `distil-whisper/distil-large-v2` does not support language parameter. example: en-US model_config: type: object description: >- Additional model-specific configuration parameters. Only allowed with `deepgram/nova-3` model. Can include Deepgram-specific options such as `smart_format`, `punctuate`, `diarize`, `utterance`, `numerals`, and `language`. If `language` is provided both as a top-level parameter and in `model_config`, the top-level parameter takes precedence. additionalProperties: true example: smart_format: true punctuate: true required: - model AudioTranscriptionResponse: type: object description: >- Response fields vary by model. `distil-whisper/distil-large-v2` returns `text`, `duration`, and `segments` in `verbose_json` mode. `openai/whisper-large-v3-turbo` returns `text` only. `deepgram/nova-3` returns `text` and, depending on `model_config`, may include `words` with per-word timestamps and speaker labels. properties: text: type: string description: The transcribed text for the audio file. duration: type: number description: >- The duration of the audio file in seconds. Returned by `distil-whisper/distil-large-v2` and `deepgram/nova-3` when `response_format` is `verbose_json`. Not returned by `openai/whisper-large-v3-turbo`. segments: type: array description: >- Segments of the transcribed text and their corresponding details. Returned by `distil-whisper/distil-large-v2` when `response_format` is `verbose_json`. Not returned by `openai/whisper-large-v3-turbo`. items: $ref: '#/components/schemas/AudioTranscriptionResponseSegments' words: type: array description: >- Word-level timestamps and optional speaker labels. Only returned by `deepgram/nova-3` when word-level output is enabled via `model_config`. items: $ref: '#/components/schemas/AudioTranscriptionResponseWord' required: - text HTTPValidationError: title: HTTPValidationError type: object properties: detail: title: Detail type: array items: $ref: '#/components/schemas/ValidationError' AudioTranscriptionResponseSegments: type: object properties: id: type: number description: Unique identifier of the segment. start: type: number description: Start time of the segment in seconds. end: type: number description: End time of the segment in seconds. text: type: string description: Text content of the segment. required: - id - start - end - text AudioTranscriptionResponseWord: type: object description: >- Word-level timing detail. Only present when using `deepgram/nova-3` with `model_config` options that enable word timestamps. properties: word: type: string description: The transcribed word. start: type: number description: Start time of the word in seconds. end: type: number description: End time of the word in seconds. confidence: type: number description: Confidence score for the word (0.0 to 1.0). speaker: type: integer description: >- Speaker index. Only present when diarization is enabled via `model_config`. required: - word - start - end ValidationError: title: ValidationError required: - loc - msg - type type: object properties: loc: title: Location type: array items: anyOf: - type: string - type: integer msg: title: Message type: string type: title: Error Type type: string securitySchemes: bearerAuth: scheme: bearer type: http ````