From 5ea2d47d3998c9e5d85c21f3e525e36b3d7f7516 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radek=20Sedl=C3=A1k?= Date: Tue, 17 Feb 2026 21:36:19 +0100 Subject: [PATCH] feat: Add support for private endpoint in Azure STT --- changelog/3764.added.md | 1 + src/pipecat/services/azure/stt.py | 4 ++++ 2 files changed, 5 insertions(+) create mode 100644 changelog/3764.added.md diff --git a/changelog/3764.added.md b/changelog/3764.added.md new file mode 100644 index 000000000..5da82f0c1 --- /dev/null +++ b/changelog/3764.added.md @@ -0,0 +1 @@ +- Added support for specifying private endpoints for Azure Speech-to-Text, enabling use in private networks behind firewalls. \ No newline at end of file diff --git a/src/pipecat/services/azure/stt.py b/src/pipecat/services/azure/stt.py index 1bc7ec70a..cc4fcb7ae 100644 --- a/src/pipecat/services/azure/stt.py +++ b/src/pipecat/services/azure/stt.py @@ -63,6 +63,7 @@ class AzureSTTService(STTService): region: str, language: Language = Language.EN_US, sample_rate: Optional[int] = None, + private_endpoint: Optional[str] = None, endpoint_id: Optional[str] = None, ttfs_p99_latency: Optional[float] = AZURE_TTFS_P99, **kwargs, @@ -74,6 +75,8 @@ class AzureSTTService(STTService): region: Azure region for the Speech service (e.g., 'eastus'). language: Language for speech recognition. Defaults to English (US). sample_rate: Audio sample rate in Hz. If None, uses service default. + private_endpoint: Private endpoint for STT behind firewall. + See https://docs.azure.cn/en-us/ai-services/speech-service/speech-services-private-link?tabs=portal endpoint_id: Custom model endpoint id. ttfs_p99_latency: P99 latency from speech end to final transcript in seconds. Override for your deployment. See https://github.com/pipecat-ai/stt-benchmark @@ -85,6 +88,7 @@ class AzureSTTService(STTService): subscription=api_key, region=region, speech_recognition_language=language_to_azure_language(language), + endpoint=private_endpoint, ) if endpoint_id: