Uploading audio files for transcription

    If you don't have publicly accessible audio URLs, you can upload your audio file directly to the API. All uploads are immediately deleted after transcription, we do not store uploads.

    Upload your Audio File

    First, you'll need to upload your audio file to the API. The API requires the "Transfer-Encoding: chunked" header, and expects your upload to be streamed up using Chunked Transfer Encoding. Most http libraries have a nice interface for handling streaming uploads. For example, in Python the requests library has a simple way to do Chunked Transfer Encoding uploads.

    A dead simple example in cURL looks like this:

    Once your upload finishes, you'll get back a JSON response like this:

    {"upload_url": "https://cdn.assemblyai.com/upload/ccbbbfaf-f319-4455-9556-272d48faaf7f"}

    The "upload_url" is a private URL, accessible only to our backend servers, that you can use when submitting transcriptions to /v2/transcript.

    Submit your Upload for Transcription

    Now that your audio file is uploaded, you can submit it for transcription just like any normal audio file.

    For more info on the complete transcription process, check out the guide on Transcribing an audio file/recording.