POST /accounts/{account_id}/ai/run/@cf/openai/whisper-large-v3-turbo
Execute @cf/openai/whisper-large-v3-turbo model.Servers
- https://api.cloudflare.com/client/v4
Path parameters
| Name | Type | Required | Description |
|---|---|---|---|
account_id |
String | Yes |
Request headers
| Name | Type | Required | Description |
|---|---|---|---|
Content-Type |
String | Yes |
The media type of the request body.
Default value: "application/json" |
Query parameters
| Name | Type | Required | Description |
|---|---|---|---|
tags |
String | No | |
queueRequest |
String | No |
Request body fields
| Name | Type | Required | Description |
|---|---|---|---|
beam_size |
Integer | No |
The number of beams to use in beam search decoding. Higher values may improve accuracy at the cost of speed. Default value: 5 |
condition_on_previous_text |
Boolean | No |
Whether to condition on previous text during transcription. Setting to false may help prevent hallucination loops. Default value: true |
prefix |
String | No |
The prefix appended to the beginning of the output of the transcription and can guide the transcription result. |
vad_filter |
Boolean | No |
Preprocess the audio with a voice activity detection model. Default value: false |
audio |
Yes | ||
hallucination_silence_threshold |
Number | No |
Optional threshold (in seconds) to skip silent periods that may cause hallucinations. |
log_prob_threshold |
Number | No |
Threshold for filtering out segments with low average log probability, indicating low confidence. Default value: -1 |
no_speech_threshold |
Number | No |
Threshold for detecting no-speech segments. Segments with no-speech probability above this value are skipped. Default value: 0.6 |
compression_ratio_threshold |
Number | No |
Threshold for filtering out segments with high compression ratio, which often indicate repetitive or hallucinated text. Default value: 2.4 |
initial_prompt |
String | No |
A text prompt to help provide context to the model on the contents of the audio. |
task |
String | No |
Supported tasks are 'translate' or 'transcribe'. Default value: "transcribe" |
language |
String | No |
The language of the audio being transcribed or translated. |
How to start integrating
- Add HTTP Task to your workflow definition.
- Search for the API you want to integrate with and click on the name.
- This loads the API reference documentation and prepares the Http request settings.
- Click Test request to test run your request to the API and see the API's response.