mirror of
https://github.com/dograh-hq/dograh.git
synced 2026-07-19 11:41:04 +02:00
ade0ee9104
The OpenAI realtime factory already reads `language` from the realtime
config, but builds `InputAudioTranscription()` without it, so the language
is silently dropped and the model auto-detects on every utterance.
On 8kHz telephony audio this misfires badly: in our production tests a
Brazilian Portuguese speaker was transcribed as English, French and Chinese
within a single call, which then corrupted downstream extraction.
Every other STT branch in `create_stt_service` already honours
`language` (Deepgram, Google, Cartesia, Dograh, Sarvam), and
`GoogleRealtimeLLMConfiguration` already exposes a `language` field for
Gemini Live. This brings the OpenAI realtime provider in line with both.
- expose `language` on `OpenAIRealtimeLLMConfiguration` (optional,
defaults to None -> unchanged auto-detect behaviour)
- pass it through to `InputAudioTranscription`, which already accepts it
Verified against pipecat: the session now carries
`{"transcription": {"model": "gpt-realtime-whisper", "language": "pt"}}`.
Co-authored-by: Liberty Card <tecnologialibertycard@gmail.com>
|
||
|---|---|---|
| .. | ||
| auth | ||
| campaign | ||
| configuration | ||
| filesystem | ||
| gen_ai | ||
| gender | ||
| integrations | ||
| pipecat | ||
| reports | ||
| telephony | ||
| voice_prompting_guide | ||
| worker_sync | ||
| workflow | ||
| call_concurrency.py | ||
| managed_model_services.py | ||
| mps_billing.py | ||
| mps_service_key_client.py | ||
| organization_context.py | ||
| organization_preferences.py | ||
| posthog_client.py | ||
| quota_service.py | ||
| storage.py | ||
| tool_management.py | ||
| user_onboarding.py | ||
| workflow_run_artifacts.py | ||
| workflow_run_billing.py | ||