This topic was automatically generated from Slack. You can find the original thread here.
I’m trying to send a file to the whisper api and it keeps giving me an error saying it can’t find the file in the tmp directory. Is there any way you can help?
I’m sorry to hear you’re having trouble with sending a file to the Whisper API. To help you better, I need more information about your current implementation. Can you please provide the code you’re using to send the file and any additional details about the error message you’re encountering? This will help me understand the issue and provide a solution.
Does this help? OpenAI (ChatGPT) Account
Credentials are encrypted. Revoke anytime.
Audio Upload Type
Are you uploading an audio file from
your workflow’s /tmp directory, or providing a URL to the file?
Language
Optional. The language of the input audio. Supplying the input language will improve accuracy and latency.
File Path
/tmp/{{steps.trigger.event.name}}
A path to your audio file to transcribe, e.g. /tmp/audio.mp3. Your audio file must be in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm. Add the appropriate extension (mp3, mp4, etc.) on your filename — OpenAI uses the extension to determine the file type. See the Pipedream docs on saving files to /tmp
Response Format
Optional. The format of the response. The default is
json.