Skip to content

docs: update for pipecat PR #4430 #799

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
markbackman wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: update for pipecat PR #4430 #799

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion api-reference/server/services/stt/deepgram.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -290,6 +290,12 @@ Supports the standard [service connection events](/api-reference/server/events/s
Whether the bot should be interrupted when Flux detects user speech.
</ParamField>

<ParamField path="watchdog_min_timeout" type="float" default="0.5">
Minimum silence duration in seconds before the watchdog sends silence to
prevent dangling turns. The actual threshold is `max(chunk_duration * 2,
watchdog_min_timeout)`, adapting automatically to the audio chunk size in use.
</ParamField>

### Settings

Runtime-configurable settings passed via the `settings` constructor argument using `DeepgramFluxSTTService.Settings(...)`. These can be updated mid-conversation with `STTUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details.
Expand Down Expand Up @@ -545,6 +551,12 @@ Supports the standard [service connection events](/api-reference/server/events/s
Whether to interrupt the bot when Flux detects user speech.
</ParamField>

<ParamField path="watchdog_min_timeout" type="float" default="0.5">
Minimum silence duration in seconds before the watchdog sends silence to
prevent dangling turns. The actual threshold is `max(chunk_duration * 2,
watchdog_min_timeout)`, adapting automatically to the audio chunk size in use.
</ParamField>

<ParamField
path="settings"
type="DeepgramFluxSageMakerSTTService.Settings"
Expand Down Expand Up @@ -634,7 +646,7 @@ await task.queue_frame(
- **EagerEndOfTurn**: Enabling `eager_eot_threshold` provides faster response times by predicting end-of-turn before it is confirmed. EagerEndOfTurn transcripts are pushed as `InterimTranscriptionFrame`s. If the user resumes speaking, a `TurnResumed` event is fired.
- **Multilingual support**: Use the `flux-general-multi` model with `language_hints` to bias transcription toward specific languages (EN, ES, FR, DE, HI, RU, PT, JA, IT, NL). `TranscriptionFrame.language` reflects the detected language for each turn. Omit hints for auto-detection or pass a subset to bias toward expected languages.
- **SageMaker deployment**: Requires a Deepgram Flux model deployed to an AWS SageMaker endpoint. Unlike Nova models, Flux provides native turn detection and does not require external VAD.
- **No KeepAlive needed**: The Flux protocol uses a watchdog mechanism that sends silence when needed to maintain the connection, so manual KeepAlive messages are not required.
- **No KeepAlive needed**: The Flux protocol uses a dynamic watchdog mechanism that sends silence when needed to maintain the connection (threshold: `max(chunk_duration * 2, watchdog_min_timeout)`), so manual KeepAlive messages are not required.

### Event Handlers

Expand Down
Loading