diff --git a/changelog/4464.added.2.md b/changelog/4464.added.2.md new file mode 100644 index 000000000..094948ff7 --- /dev/null +++ b/changelog/4464.added.2.md @@ -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`). diff --git a/changelog/4464.added.3.md b/changelog/4464.added.3.md new file mode 100644 index 000000000..8fc7e573e --- /dev/null +++ b/changelog/4464.added.3.md @@ -0,0 +1 @@ +- Added `sanitize_text_for_tts()` utility (`pipecat.utils.text.tts_text_sanitizer`) that strips markdown formatting (fenced code blocks, headers, bold/italic, tables, blockquotes, inline code) and emojis from text before sending it to a TTS service. diff --git a/changelog/4464.added.md b/changelog/4464.added.md new file mode 100644 index 000000000..9935c47f0 --- /dev/null +++ b/changelog/4464.added.md @@ -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.