Merge pull request #4464 from pipecat-ai/filipi/nvidia_sagemaker

NVidia sagemaker - TTS and STT services
This commit is contained in:
Filipi da Silva Fuchter
2026-05-13 07:53:26 -03:00
committed by GitHub
8 changed files with 986 additions and 2 deletions

View File

@@ -0,0 +1 @@
- Added NVIDIA Magpie TTS services via AWS SageMaker: `NvidiaSageMakerHTTPTTSService` (single HTTP invocation, streams raw PCM back) and `NvidiaSageMakerWebsocketTTSService` (persistent HTTP/2 bidi-stream with full interruption support via `InterruptibleTTSService`).

1
changelog/4464.added.md Normal file
View File

@@ -0,0 +1 @@
- Added `NvidiaSageMakerWebsocketSTTService` for streaming speech recognition using NVIDIA Nemotron ASR via an AWS SageMaker bidirectional-stream endpoint. Produces `InterimTranscriptionFrame` and `TranscriptionFrame` frames, is VAD-aware, and automatically reconnects on error.