openai · OpenAI Platform Docs
Speech to text
Teaches how to implement speech-to-text workflows using OpenAI's Audio API, including transcription, translation, speaker diarization, and handling longer audio inputs with specific model parameters.
Derived skill
Files assembled from official documentation
Viewing SKILL.md
Speech to text
Teaches how to implement speech-to-text workflows using OpenAI's Audio API, including transcription, translation, speaker diarization, and handling longer audio inputs with specific model parameters.
When To Use
Use when you need to implement audio transcription, translate foreign language audio into English, or generate speaker-labeled transcripts from audio files.
Reference Files
| File | Contains | Use For |
|---|---|---|
SKILL.md | Entry point: scope, routing table, and workflow. | Start here. |
docs/speech-to-text-workflow-guide.md | A guide covering OpenAI Audio API endpoints for transcriptions, translations, and speaker diarization. | Questions about a guide covering OpenAI Audio API endpoints for transcriptions, translations, and speaker diarization. |
examples/speech-to-text-openai-speech-to-text-transcriptions-create.javascript | A JavaScript code example demonstrating how to use the OpenAI client to transcribe an audio file using the transcriptions create method. | Exact payloads, commands, or snippets shown in A JavaScript code example demonstrating how to use the OpenAI client to transcribe an audio file using the transcript... |
examples/speech-to-text-openai-speech-to-text-transcription.python | A Python script demonstrating how to use the OpenAI client to transcribe an audio file using the speech-to-text API. | Exact payloads, commands, or snippets shown in A Python script demonstrating how to use the OpenAI client to transcribe an audio file using the speech-to-text API. |
examples/speech-to-text-openai-speech-to-text-transcriptions-create.cli | A CLI command demonstrating how to create an audio transcription using the OpenAI speech-to-text API. | Exact payloads, commands, or snippets shown in A CLI command demonstrating how to create an audio transcription using the OpenAI speech-to-text API. |
examples/speech-to-text-openai-speech-to-text-transcriptions-curl-request.bash | A curl command demonstrating how to send an audio file to the OpenAI transcriptions endpoint for speech-to-text conversion. | Exact payloads, commands, or snippets shown in A curl command demonstrating how to send an audio file to the OpenAI transcriptions endpoint for speech-to-text conve... |
examples/speech-to-text-openai-speech-to-text-transcription.examplecontent | A text-based example demonstrating the structure and content used for speech-to-text transcription requests. | Exact payloads, commands, or snippets shown in A text-based example demonstrating the structure and content used for speech-to-text transcription requests. |
examples/speech-to-text-openai-speech-to-text-transcriptions-create-2.javascript | A JavaScript example demonstrating how to use the OpenAI client to transcribe an audio file using the transcriptions create method. | Exact payloads, commands, or snippets shown in A JavaScript example demonstrating how to use the OpenAI client to transcribe an audio file using the transcriptions... |
examples/speech-to-text-openai-speech-to-text-transcription-2.python | A Python script using the OpenAI client to transcribe an MP3 audio file into text using the transcription API. | Exact payloads, commands, or snippets shown in A Python script using the OpenAI client to transcribe an MP3 audio file into text using the transcription API. |
examples/speech-to-text-openai-speech-to-text-transcriptions-curl-request-2.bash | A curl command demonstrating how to send an audio file to the OpenAI transcriptions endpoint using multipart/form-data. | Exact payloads, commands, or snippets shown in A curl command demonstrating how to send an audio file to the OpenAI transcriptions endpoint using multipart/form-data. |
examples/speech-to-text-openai-speech-to-text-transcription.javascript | A JavaScript code example demonstrating how to use the OpenAI API to create audio transcriptions from a file using the transcription create method. | Exact payloads, commands, or snippets shown in A JavaScript code example demonstrating how to use the OpenAI API to create audio transcriptions from a file using th... |
examples/speech-to-text-openai-speech-to-text-transcription-3.python | A Python script demonstrating how to use the OpenAI client to transcribe an audio file using the transcription create method. | Exact payloads, commands, or snippets shown in A Python script demonstrating how to use the OpenAI client to transcribe an audio file using the transcription create... |
examples/speech-to-text-openai-speech-to-text-transcription-curl-request.bash | A curl command demonstrating how to send an audio file to the OpenAI transcription endpoint using multipart/form-data. | Exact payloads, commands, or snippets shown in A curl command demonstrating how to send an audio file to the OpenAI transcription endpoint using multipart/form-data. |
examples/speech-to-text-openai-speech-to-text-audio-translation.javascript | A JavaScript example demonstrating how to use the OpenAI Whisper model to translate audio files into text. | Exact payloads, commands, or snippets shown in A JavaScript example demonstrating how to use the OpenAI Whisper model to translate audio files into text. |
examples/speech-to-text-openai-speech-to-text-whisper-translation.python | A Python script using the OpenAI client to translate an MP3 audio file into text using the whisper-1 model. | Exact payloads, commands, or snippets shown in A Python script using the OpenAI client to translate an MP3 audio file into text using the whisper-1 model. |
examples/speech-to-text-openai-speech-to-text-audio-translation-curl.bash | A curl command demonstrating how to use the OpenAI Whisper API to translate audio files from German to English. | Exact payloads, commands, or snippets shown in A curl command demonstrating how to use the OpenAI Whisper API to translate audio files from German to English. |
examples/speech-to-text-openai-speech-to-text-audio-transcription.examplecontent | A text sample of the spoken content used to demonstrate the speech to text transcription process. | Exact payloads, commands, or snippets shown in A text sample of the spoken content used to demonstrate the speech to text transcription process. |
examples/speech-to-text-openai-speech-to-text-whisper-transcription.javascript | A JavaScript example demonstrating how to use the OpenAI Whisper model to create a transcription with word-level timestamps. | Exact payloads, commands, or snippets shown in A JavaScript example demonstrating how to use the OpenAI Whisper model to create a transcription with word-level time... |
examples/speech-to-text-openai-speech-to-text-whisper-python-transcription.python | A Python script demonstrating how to use the OpenAI Whisper model to transcribe an audio file with word-level timestamp granularity. | Exact payloads, commands, or snippets shown in A Python script demonstrating how to use the OpenAI Whisper model to transcribe an audio file with word-level timesta... |
examples/speech-to-text-openai-speech-to-text-whisper-transcription-curl.bash | A curl command demonstrating how to request a transcription from the Whisper model using the OpenAI API with verbose JSON response format. | Exact payloads, commands, or snippets shown in A curl command demonstrating how to request a transcription from the Whisper model using the OpenAI API with verbose... |
examples/speech-to-text-openai-speech-to-text-python-audio-segmentation.python | A Python script using pydub to segment an mp3 audio file into ten-minute chunks for processing. | Exact payloads, commands, or snippets shown in A Python script using pydub to segment an mp3 audio file into ten-minute chunks for processing. |
examples/speech-to-text-openai-speech-to-text-transcriptions-create-3.javascript | A JavaScript example demonstrating how to use the OpenAI client to create a transcription from an audio file using the transcriptions create method. | Exact payloads, commands, or snippets shown in A JavaScript example demonstrating how to use the OpenAI client to create a transcription from an audio file using th... |
examples/speech-to-text-openai-speech-to-text-python-transcription.python | A Python script demonstrating how to use the OpenAI client to transcribe an audio file using the speech-to-text API. | Exact payloads, commands, or snippets shown in A Python script demonstrating how to use the OpenAI client to transcribe an audio file using the speech-to-text API. |
examples/speech-to-text-openai-speech-to-text-transcriptions-curl-request-3.bash | A curl command demonstrating how to send an audio file to the OpenAI transcriptions endpoint using multipart/form-data. | Exact payloads, commands, or snippets shown in A curl command demonstrating how to send an audio file to the OpenAI transcriptions endpoint using multipart/form-data. |
examples/speech-to-text-openai-speech-to-text-transcriptions-stream.javascript | A JavaScript example demonstrating how to use the OpenAI API to create a streaming transcription from an audio file. | Exact payloads, commands, or snippets shown in A JavaScript example demonstrating how to use the OpenAI API to create a streaming transcription from an audio file. |
examples/speech-to-text-openai-speech-to-text-python-streaming-transcription.python | A Python script demonstrating how to use the OpenAI client to create a streaming transcription from an audio file. | Exact payloads, commands, or snippets shown in A Python script demonstrating how to use the OpenAI client to create a streaming transcription from an audio file. |
examples/speech-to-text-openai-speech-to-text-transcriptions-curl-request-4.bash | A curl command demonstrating how to send an audio file to the OpenAI Whisper transcription endpoint using multipart/form-data. | Exact payloads, commands, or snippets shown in A curl command demonstrating how to send an audio file to the OpenAI Whisper transcription endpoint using multipart/f... |
examples/speech-to-text-openai-speech-to-text-realtime-websocket-url.text | The WebSocket URL used for initiating real-time speech to text transcription via the OpenAI API. | Exact payloads, commands, or snippets shown in The WebSocket URL used for initiating real-time speech to text transcription via the OpenAI API. |
examples/speech-to-text-openai-speech-to-text-transcription-session-update.json | A JSON object representing a transcription session update request with audio format and turn detection parameters. | Exact payloads, commands, or snippets shown in A JSON object representing a transcription session update request with audio format and turn detection parameters. |
examples/speech-to-text-openai-speech-to-text-audio-buffer-append.json | A JSON object representing the input audio buffer append operation for the OpenAI speech-to-text API. | Exact payloads, commands, or snippets shown in A JSON object representing the input audio buffer append operation for the OpenAI speech-to-text API. |
examples/speech-to-text-openai-speech-to-text-realtime-transcription-session.json | A JSON schema defining the structure for a realtime transcription session object including audio format and turn detection parameters. | Exact payloads, commands, or snippets shown in A JSON schema defining the structure for a realtime transcription session object including audio format and turn dete... |
examples/speech-to-text-openai-speech-to-text-realtime-transcription-session-post.text | A text representation of a POST request to the v1/realtime/transcription_sessions endpoint for initiating speech to text sessions. | Exact payloads, commands, or snippets shown in A text representation of a POST request to the v1/realtime/transcriptionsessions endpoint for initiating speech to te... |
examples/speech-to-text-openai-speech-to-text-whisper-transcription-2.javascript | A JavaScript example demonstrating how to use the OpenAI Whisper model to transcribe an audio file with a custom prompt. | Exact payloads, commands, or snippets shown in A JavaScript example demonstrating how to use the OpenAI Whisper model to transcribe an audio file with a custom prompt. |
examples/speech-to-text-openai-speech-to-text-whisper-python-transcription-2.python | A Python script using the OpenAI client to transcribe an MP3 audio file using the whisper-1 model. | Exact payloads, commands, or snippets shown in A Python script using the OpenAI client to transcribe an MP3 audio file using the whisper-1 model. |
examples/speech-to-text-openai-speech-to-text-transcriptions-curl-request-5.bash | A curl command demonstrating how to send an audio file to the OpenAI Whisper API for transcription using multipart/form-data. | Exact payloads, commands, or snippets shown in A curl command demonstrating how to send an audio file to the OpenAI Whisper API for transcription using multipart/fo... |
examples/speech-to-text-openai-speech-to-text-transcription-correction.javascript | A JavaScript example demonstrating how to use a system prompt to correct spelling discrepancies in transcribed text using OpenAI's speech-to-text capabilities. | Exact payloads, commands, or snippets shown in A JavaScript example demonstrating how to use a system prompt to correct spelling discrepancies in transcribed text u... |
examples/speech-to-text-openai-speech-to-text-python-transcription-correction.python | A Python script demonstrating how to use OpenAI's speech-to-text capabilities combined with a system prompt to correct spelling discrepancies in transcribed text. | Exact payloads, commands, or snippets shown in A Python script demonstrating how to use OpenAI's speech-to-text capabilities combined with a system prompt to correc... |
What This Skill Covers
- The Audio API provides two speech to text endpoints:
- Main sections:
Quickstart,Transcriptions,Speaker diarization,Translations,Supported languages.
Workflow
- Open the most relevant file under
docs/for the exact documented workflow and wording. - Open
schemas/files for exact structured contracts. - Open
examples/files for concrete requests, commands, snippets, and manifests. - Do not add behavior or configuration that is not present in the attached source files.
Canonical source: https://developers.openai.com/api/docs/guides/speech-to-text.md