🐛(summary) explicit transcription response format

We should be able to use other transcription services,
those usually relie on response_format="diarized_json"
to produce what we need.

Note that as part of this change, we stop using
openai library for making this call to avoid
casting the result to a payload that doesn't
contain the elements we used to rely on.
(setting this specific format auto cast the
results in openai lib). We keep the old
result class used.
This commit is contained in:
Florent Chehab
2026-06-12 12:47:02 +02:00
parent 5c27aba00f
commit 9b7c449ca5
4 changed files with 56 additions and 10 deletions
-1
View File
@@ -80,7 +80,6 @@ sequenceDiagram
| whisperx_api_key | Secret | — | API key for accessing WhisperX. |
| whisperx_base_url | String | `"https://api.whisperx.com/v1"` | Base URL for the WhisperX API. |
| whisperx_asr_model | String | `"whisper-1"` | ASR model used for transcription. |
| whisperx_max_retries | Integer | `0` | Maximum number of retries for WhisperX API requests. |
| webhook_max_retries | Integer | `2` | Maximum retries for webhook requests. |
| webhook_status_forcelist | List[Int] | `[502, 503, 504]` | HTTP status codes triggering webhook retry. |
| webhook_backoff_factor | Float | `0.1` | Exponential backoff factor for webhook retries. |