Observability

Rasa emits OpenTelemetry traces for monitoring conversations. This page catalogs each voice trace span and explains how to interpret its attributes and events. Availability and privacy labels are summarized in How to read attribute tables.

Configure tracing

Add a tracing section to integrations.yml. Choose Langfuse, an OTLP collector, or Jaeger:

integrations.yml

# OTLP collector (gRPC)
tracing:
  type: otlp
  endpoint: <your-otel-collector-endpoint>
  insecure: true

integrations.yml

# Jaeger
tracing:
  type: jaeger
  host: localhost
  port: 4317

integrations.yml

# Langfuse
tracing:
  type: langfuse
  public_key: ${LANGFUSE_PUBLIC_KEY}
  private_key: ${LANGFUSE_SECRET_KEY}
  host: https://cloud.langfuse.com

For OTLP, replace the endpoint with your collector’s gRPC endpoint. To use Langfuse together with OTLP or Jaeger, list both under tracing:. Full field reference: integrations.yml → Tracing.

Voice traces

When voice tracing is enabled, each call produces a trace that follows provider connections, input handling, engine turns, speech synthesis, audio playback, and call recording when recording is enabled. This section catalogs those spans, their attributes, and the events recorded on each span.

Typical trace

The tree shows common parent-child relationships, not execution order.

📞 voice call
├── 🔌 connect asr
├── 🔌 connect tts
├── 📝 transcribe audio
├── ⚡ handle barge-in
├── 🔢 handle dtmf
├── ⏱️ handle silence
├── 🔄 handle turn
│   ├── 🗣️ synthesize speech
│   └── 🔊 play audio
├── ⚠️ process channel message (failures only)
├── ⚠️ compose event (failures only)
├── 💾 store call recording (when recording is enabled)
├── 🔌 disconnect asr
└── 🔌 disconnect tts

Content capture

Content capture is off by default. Set the RASA_VOICE_CAPTURE_CONTENT environment variable to true, 1, or yes (case-insensitive, surrounding whitespace ignored) to include supported transcript and generated-text attributes in traces.

Content capture never includes raw audio, partial transcripts, or DTMF digits. Audio is reported only as byte and chunk totals. Call-recording storage locators are identifiers, not content, and are emitted without this gate.

Attributes shared by voice spans

The following correlation fields are added to every span created inside an active voice call. They are not included when the span does not belong to a voice call.

Attribute	Type	Availability	Data classification	Description
`rasa.conversation.id`	string	Inside a voice call	Identifier	Conversation ID used to correlate the voice call with its conversation.
`voice.channel.call_id`	string	Inside a voice call	Identifier	Channel-assigned call ID. It can differ from the conversation ID.

Every span that Rasa marks ERROR also has:

Attribute	Type	Availability	Data classification	Description
`error.type`	string	On error	Operational	Exception class name, such as `RuntimeError`.

exception events can include messages and stack traces. RASA_VOICE_CAPTURE_CONTENT does not redact them.

`voice call` span

Detail	Description
Span kind	`INTERNAL`
Lifetime	Opens before provider and session setup. Ends after active processing, provider disconnects, and transport teardown.
Typical parent	The active OpenTelemetry span, when present. Otherwise `voice call` is the trace root.
Error behavior	Failures during setup, active processing, or teardown mark it `ERROR`. Cancellation alone does not.

Attributes

Attribute	Type	Availability	Data classification	Description
`rasa.conversation.id`	string	Always	Identifier	Conversation correlation ID.
`voice.channel.call_id`	string	Always	Identifier	Channel call ID.
`voice.channel.name`	string	Always	Operational	Voice channel name.
`voice.asr.provider`	string	When configured	Operational	Configured ASR provider.
`voice.tts.provider`	string	When configured	Operational	Configured TTS provider.
`voice.locale`	string	When known	Operational	Call locale at span creation.
`audio.input.bytes.total`	integer	At span end	Operational	Total incoming audio bytes observed during the call.
`audio.input.chunk.count`	integer	At span end	Operational	Number of incoming audio chunks observed during the call.
`audio.output.bytes.total`	integer	At span end	Operational	Total outgoing audio bytes delivered during the call.
`audio.output.chunk.count`	integer	At span end	Operational	Number of outgoing audio chunks delivered during the call.
`error.type`	string	On error	Operational	Present only when the call is marked `ERROR`.

Events

Event	Description	Attribute	Type	Availability	Data classification
`voice.call_started`	Call setup completed and the session started.	None	—	—	—
`voice.hangup_requested`	The agent requested a hangup. Goodbye audio can still finish first.	None	—	—	—
`voice.disconnect`	The channel reported a transport-level disconnect.	None	—	—	—
`voice.call_ended`	Active call processing handed over to teardown.	None	—	—	—
`voice.turn_event_enqueued`	A voice input was processed and sent to the agent for handling.	`voice.turn_event.type`	string	Always	Operational
		`voice.queue.size`	integer	Always	Operational

voice.call_ended ends active processing, not the voice call span. Disconnect of ASR and TTS and teardown can follow.

Provider connection spans

The four connection spans are CLIENT spans. Each span covers one provider connection or disconnection attempt. A failed attempt adds error.type, records a standard exception event, and marks the span ERROR.

`connect asr` span

Opens for every ASR connection attempt, including reconnects, and ends when the attempt succeeds or fails.

Detail	Description
Span kind	`CLIENT`
Lifetime	One ASR connection attempt, including a reconnect.
Typical parent	`voice call`.
Error behavior	A failed attempt records `error.type` and a standard `exception` event and marks the span `ERROR`.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.asr.provider`	string	Always	Operational	ASR provider name.
`voice.locale`	string	When configured	Operational	Rasa language key.
`voice.asr.language`	string	When configured	Operational	Provider language key.
`voice.asr.model`	string	When configured	Operational	Provider model.
`voice.connect.reconnect`	boolean	On reconnect	Operational	`true` after an earlier successful connection.
`error.type`	string	On error	Operational	Present only on failure.

Events No custom span events. A standard exception event is recorded on failure.

`disconnect asr` span

Opens for every ASR disconnection attempt and ends when the attempt succeeds or fails. It never carries voice.connect.reconnect.

Detail	Description
Span kind	`CLIENT`
Lifetime	One ASR disconnection attempt.
Typical parent	`voice call`.
Error behavior	A failed attempt records `error.type` and a standard `exception` event and marks the span `ERROR`.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.asr.provider`	string	Always	Operational	ASR provider name.
`voice.locale`	string	When configured	Operational	Rasa language key.
`voice.asr.language`	string	When configured	Operational	Provider language key.
`voice.asr.model`	string	When configured	Operational	Provider model.
`error.type`	string	On error	Operational	Present only on failure.

Events No custom span events. A standard exception event is recorded on failure.

`connect tts` span

Opens for every TTS connection attempt, including reconnects, and ends when the attempt succeeds or fails.

Detail	Description
Span kind	`CLIENT`
Lifetime	One TTS connection attempt, including a reconnect.
Typical parent	`voice call`.
Error behavior	A failed attempt records `error.type` and a standard `exception` event and marks the span `ERROR`.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.tts.provider`	string	Always	Operational	TTS provider name.
`voice.locale`	string	When configured	Operational	Rasa language key.
`voice.tts.language`	string	When configured	Operational	Provider language key.
`voice.tts.model`	string	When configured	Operational	Provider model.
`voice.connect.reconnect`	boolean	On reconnect	Operational	`true` after an earlier successful connection.
`error.type`	string	On error	Operational	Present only on failure.

Events No custom span events. A standard exception event is recorded on failure.

`disconnect tts` span

Opens for every TTS disconnection attempt and ends when the attempt succeeds or fails. It never carries voice.connect.reconnect.

Detail	Description
Span kind	`CLIENT`
Lifetime	One TTS disconnection attempt.
Typical parent	`voice call`.
Error behavior	A failed attempt records `error.type` and a standard `exception` event and marks the span `ERROR`.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.tts.provider`	string	Always	Operational	TTS provider name.
`voice.locale`	string	When configured	Operational	Rasa language key.
`voice.tts.language`	string	When configured	Operational	Provider language key.
`voice.tts.model`	string	When configured	Operational	Provider model.
`error.type`	string	On error	Operational	Present only on failure.

Events No custom span events. A standard exception event is recorded on failure.

`transcribe audio` span

Detail	Description
Span kind	`INTERNAL`
Lifetime	One user utterance. Opens on the first partial transcript, or on a final transcript when no partial arrived, and normally closes on the final transcript. An empty final with no open utterance creates no span.
Typical parent	`voice call`.
Error behavior	An ASR stream error marks it `ERROR`. Stream teardown closes an open span without treating the missing final as an error.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.asr.provider`	string	Always	Operational	ASR provider name.
`voice.locale`	string	When configured	Operational	Rasa language key.
`voice.asr.language`	string	When configured	Operational	Provider language key.
`voice.asr.model`	string	When configured	Operational	Provider model.
`partial_transcript.count`	integer	At span end	Operational	Total number of partial transcript updates, including updates without a sampled event.
`voice.transcript.final`	string	On a final transcript when content capture is enabled	Content	Final transcript.
`error.type`	string	On error	Operational	Present only on ASR failure.

Events

Event	Description	Attribute	Type	Availability	Data classification
`voice.partial_transcript`	Sampled partial-transcript update. The first partial and then every tenth partial are recorded: 1, 11, 21, and so on.	None	—	—	—
`voice.final_transcript`	Final transcript arrived. Its text is never placed on the event.	None	—	—	—
`voice.asr_error`	The ASR stream failed. A standard `exception` event is also recorded.	None	—	—	—

Input-decision spans

Input-decision spans show how Rasa handles input received during a call before passing it to the agent. They cover spoken interruptions, keypad input, and silence timeouts. They record whether the input was accepted, ignored, or buffered, as well as any failures.

`handle barge-in` span

Detail	Description
Span kind	`INTERNAL`
Lifetime	One barge-in classification. Opens when interruptions are enabled and caller speech is evaluated as a possible interruption while agent audio is playing or waiting to be played.
Typical parent	`voice call`.
Error behavior	A classification or interruption-processing failure records `voice.barge_in_failed` and a standard `exception` event, then marks the span `ERROR`.

Attributes None beyond the shared correlation and optional failure attributes. Events

Event	Description	Attribute	Type	Availability	Data classification
`voice.barge_in_attempted`	A gated transcript entered classification.	`voice.barge_in.transcript`	string	When content capture is enabled	Content
`voice.turn_event_enqueued`	The accepted interruption was sent to the agent for processing.	`voice.turn_event.type`	string	Always	Operational
		`voice.queue.size`	integer	Always	Operational
`voice.barge_in_accepted`	The speech was accepted as a deliberate interruption.	`voice.barge_in.reason`	string	Optional	Operational
		`voice.barge_in.audio_was_playing`	boolean	When known	Operational
		`voice.barge_in.audio_was_buffered`	boolean	When known	Operational
		`voice.barge_in.transcript`	string	When content capture is enabled	Content
`voice.barge_in_ignored`	The speech was classified as not being a barge-in.	`voice.barge_in.reason`	string	Optional	Operational
		`voice.barge_in.audio_was_playing`	boolean	When known	Operational
		`voice.barge_in.audio_was_buffered`	boolean	When known	Operational
		`voice.barge_in.transcript`	string	When content capture is enabled	Content
`voice.barge_in_failed`	Classification or interruption processing failed.	None	—	—	—

voice.barge_in.audio_was_playing is true when agent audio was already audible when the transcript arrived. voice.barge_in.audio_was_buffered is true when audio was queued but not yet audible. Both can be true at once.

`handle dtmf` span

Detail	Description
Span kind	`INTERNAL`
Lifetime	One DTMF keypress decision and its resulting action.
Typical parent	`voice call`.
Error behavior	A failure adds `error.type` and a standard `exception` event and marks the span `ERROR`.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.dtmf.buffer_length`	integer	After a digit is buffered	Operational	Number of buffered digits after this keypress. Digit values are not captured.
`error.type`	string	On error	Operational	Present only on failure.

Events

Event	Description	Attribute	Type	Availability	Data classification
`voice.dtmf_started`	This keypress opened a digit-collection window.	None	—	—	—
`voice.dtmf_digit`	One digit was buffered. The value is never attached.	None	—	—	—
`voice.turn_event_enqueued`	The completed DTMF input was sent to the agent for processing.	`voice.turn_event.type`	string	Always	Operational
		`voice.queue.size`	integer	Always	Operational
`voice.dtmf_accepted`	The buffered input completed the active DTMF collect step.	None	—	—	—
`voice.dtmf_ignored`	No active DTMF collect step accepted the keypress.	None	—	—	—

`handle silence` span

Detail	Description
Span kind	`INTERNAL`
Lifetime	Starts when the caller has been silent for the configured timeout and ends when Rasa finishes handling the timeout.
Typical parent	`voice call`.
Error behavior	A failure adds `error.type` and a standard `exception` event and marks the span `ERROR`.

Attributes None beyond the shared correlation and optional failure attributes. Events

Event	Description	Attribute	Type	Availability	Data classification
`voice.silence_detected`	The armed timer fired.	None	—	—	—
`voice.turn_event_enqueued`	The silence timeout was sent to the agent for processing.	`voice.turn_event.type`	string	Always	Operational
		`voice.queue.size`	integer	Always	Operational
`voice.silence_accepted`	Rasa accepted the detected silence as a timeout.	None	—	—	—
`voice.dtmf_timeout`	The caller did not complete keypad input before the timeout, so the buffered digits were discarded.	None	—	—	—

`handle turn` span

Detail	Description
Span kind	`INTERNAL`
Lifetime	One Mantle engine turn, including engine processing and output production.
Typical parent	`voice call`.
Error behavior	An exception adds `error.type` and a standard `exception` event and marks the span `ERROR`.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.turn.index`	integer	Always	Operational	One-based turn number within the call, including lifecycle turns.
`voice.latency.rasa_processing_ms`	double	When processing duration is available	Operational	Engine processing time for the turn.
`voice.latency.user_perceived_ms`	double	When user input time and an audio or text output are available	Operational	Time from user input to the first output. Audio output takes precedence; if no audio is produced, the first text output is used.
`voice.interrupted`	boolean	When interrupted	Operational	Present and `true` when the turn was interrupted.
`error.type`	string	On error	Operational	Present only on failure.

Events

Event	Description	Attribute	Type	Availability	Data classification
`voice.filler_sent`	A filler or acknowledgement message was sent during the turn.	`voice.filler.response_name`	string	Optional	Operational
		`voice.filler.text`	string	When available and content capture is enabled	Content
`rasa.turn.response_dropped`	Cancellation skipped committing a generated agent message. Emitted once per skipped message, including fillers. Streaming audio may already have played.	`rasa.turn.response_dropped.is_filler`	boolean	Always	Operational
		`rasa.turn.response_dropped.text`	string	When available and content capture is enabled	Content

`synthesize speech` span

Detail	Description
Span kind	`INTERNAL`
Lifetime	One agent message, from the start of speech synthesis through generated, cached, or fallback audio completion. Each message gets its own span.
Typical parent	`handle turn`.
Error behavior	A TTS failure adds `error.type`, records `voice.tts_error` and a standard `exception` event, and marks the span `ERROR`. The span stays open while fallback silence is produced and closes afterward.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.tts.provider`	string	Always	Operational	TTS provider name.
`voice.locale`	string	When configured	Operational	Rasa language key.
`voice.tts.language`	string	When configured	Operational	Provider language key.
`voice.tts.model`	string	When configured	Operational	Provider model.
`voice.tts.cache_hit`	boolean	After cache lookup	Operational	Whether audio came from the TTS cache.
`voice.latency.tts_first_byte_ms`	double	When first audio is available	Operational	Speech synthesis start to the first generated, cached, or fallback audio chunk.
`audio.bytes.total`	integer	At span end	Operational	Total generated, cached, or fallback audio bytes for this message.
`audio.chunk.count`	integer	At span end	Operational	Number of generated, cached, or fallback audio chunks for this message.
`voice.tts.text`	string	When content capture is enabled	Content	Synthesized text. For streamed messages, this is the text accumulated from chunks sent to TTS.
`error.type`	string	On error	Operational	Present only on failure.

Audio totals are added when the span ends and can be zero.

Events

Event	Description	Attribute	Type	Availability	Data classification
`voice.tts_request`	A synthesis request was sent to the provider. Absent on a cache hit.	None	—	—	—
`voice.tts_cache_hit`	The audio was served from the TTS cache. Recorded instead of `voice.tts_request`.	None	—	—	—
`voice.tts_first_audio_generated`	The first generated, cached, or fallback audio chunk became available.	`voice.tts.audio_source`	string	Always	Operational
`voice.tts_complete`	Generated, cached, or fallback audio processing completed.	None	—	—	—
`voice.tts_error`	Synthesis failed.	None	—	—	—

voice.tts.audio_source is cached, generated, or fallback.

After a TTS failure, fallback audio can still produce completion and audio-total signals. The span remains ERROR.

`play audio` span

Detail	Description
Span kind	`INTERNAL`
Lifetime	One agent message’s audio delivery.
Typical parent	`handle turn`.
Error behavior	A delivery failure adds `error.type` and a standard `exception` event and marks the span `ERROR`.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.interrupted`	boolean	When interrupted	Operational	Present and `true` when barge-in cut playback short.
`voice.playback.text`	string	At span end, when content capture is enabled and TTS text is known	Content	Text that was synthesized for this delivery, including streamed chunks.
`audio.bytes.total`	integer	At span end	Operational	Bytes delivered before the span ended.
`audio.chunk.count`	integer	At span end	Operational	Chunks delivered before the span ended.
`error.type`	string	On error	Operational	Present only on delivery failure.

Events

Event	Description	Attribute	Type	Availability	Data classification
`voice.playback_start`	First audio chunk was delivered. Emitted at most once.	None	—	—	—
`voice.playback_interrupted`	A user barge-in interrupted playback. Emitted at most once.	None	—	—	—
`voice.playback_cancelled`	Audio delivery was cancelled during teardown or shutdown.	None	—	—	—
`voice.playback_finished`	Audio delivery finished. It can follow an interruption, but is suppressed after cancellation.	None	—	—	—

`store call recording` span

Opens when Rasa finalizes a call recording: encode, upload, and report the outcome. It is created only when recording is enabled for the call.

Detail	Description
Span kind	`INTERNAL`
Lifetime	One finalize of the call recording, from encode and upload through the terminal outcome.
Typical parent	`voice call`.
Error behavior	Encode or upload failure records `voice.recording_failed`, adds `error.type`, and marks the span `ERROR`. It does not record a standard `exception` event or put the exception message on the span status. An empty recording is skipped and is not an error.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.recording.storage.provider`	string	Always	Operational	Configured storage provider, such as `s3`, `gcs`, `azure`, or `local`.
`voice.recording.chunk_count`	integer	Always	Operational	Number of audio chunks captured before finalization.
`voice.recording.status`	string	At span end	Operational	Terminal outcome: `available`, `failed`, or `skipped`.
`voice.recording.content_type`	string	When the recording is available	Operational	MIME type of the stored file, such as `audio/wav`.
`voice.recording.bucket`	string	When the recording is available	Identifier	Storage bucket or container. Empty for local files.
`voice.recording.key`	string	When the recording is available	Identifier	Object key or filename of the stored recording.
`voice.recording.uri`	string	When the recording is available	Identifier	Locator for the stored recording (`s3://`, `gs://`, `https://`, or `file://`). Does not include credentials.
`error.type`	string	On error	Operational	Exception class name. Present only when status is `failed`.

Storage locators (bucket, key, uri) identify where the recording file lives. They are not the audio itself and are not gated by content capture. A file:// URI can include a local filesystem path.

Events

Event	Description	Attribute	Type	Availability	Data classification
`voice.recording_available`	The recording was encoded and stored.	None	—	—	—
`voice.recording_skipped`	No audio was captured, so nothing was stored.	None	—	—	—
`voice.recording_failed`	Encoding or storage failed.	None	—	—	—

Each span records exactly one of these events.

Failure-only spans

These spans appear only when an operation fails. They are backdated to the start of the failed operation and end when the failure is recorded.

`process channel message` span

Covers a failed channel-message processing operation. It has only the shared correlation and failure attributes.

Detail	Description
Span kind	`INTERNAL`
Lifetime	The failed channel operation, backdated to its start and ended when the failure is recorded.
Typical parent	`voice call`.
Error behavior	Always records `error.type` and a standard `exception` event and has `ERROR` status.

Attributes

Attribute	Type	Availability	Data classification	Description
`error.type`	string	Always	Operational	Exception class name.

Events No custom span events. A standard exception event is recorded.

`compose event` span

Appears when Rasa fails while interpreting a voice-channel input, such as caller speech, keypad input, or a silence timeout, and preparing it for the agent.

Detail	Description
Span kind	`INTERNAL`
Lifetime	The failed input-processing attempt, from when Rasa began interpreting the input until the failure was recorded.
Typical parent	`voice call`.
Error behavior	Always records `error.type` and a standard `exception` event and has `ERROR` status.

Attributes

Attribute	Type	Availability	Data classification	Description
`voice.turn_event.type`	string	When event type is available	Operational	Type of voice input that could not be processed.
`error.type`	string	Always	Operational	Exception class name.

Events No custom span events. A standard exception event is recorded.

How to read attribute tables

The Availability column describes when an attribute is eligible or written relative to an emitted span. The Data classification column uses these privacy labels:

Operational — contains no spoken content or direct call identifier.
Identifier — correlates a call or conversation, locates a stored recording, or otherwise may be customer data.
Content — contains transcript or generated text and is emitted only when content capture is enabled.

File Reference

Language

Tools

Customizations

Runtime

Prompts

Schemas

Observability

Configure tracing

Voice traces

Typical trace

Content capture

Attributes shared by voice spans

`voice call` span

Provider connection spans

`connect asr` span

`disconnect asr` span

`connect tts` span

`disconnect tts` span

`transcribe audio` span

Input-decision spans

`handle barge-in` span

`handle dtmf` span

`handle silence` span

`handle turn` span

`synthesize speech` span

`play audio` span

`store call recording` span

Failure-only spans

`process channel message` span

`compose event` span

How to read attribute tables

​Configure tracing

​Voice traces

​Typical trace

​Content capture

​Attributes shared by voice spans

​voice call span

​Provider connection spans

​connect asr span

​disconnect asr span

​connect tts span

​disconnect tts span

​transcribe audio span

​Input-decision spans

​handle barge-in span

​handle dtmf span

​handle silence span

​handle turn span

​synthesize speech span

​play audio span

​store call recording span

​Failure-only spans

​process channel message span

​compose event span

​How to read attribute tables

Configure tracing

Voice traces

Typical trace

Content capture

Attributes shared by voice spans

`voice call` span

Provider connection spans

`connect asr` span

`disconnect asr` span

`connect tts` span

`disconnect tts` span

`transcribe audio` span

Input-decision spans

`handle barge-in` span

`handle dtmf` span

`handle silence` span

`handle turn` span

`synthesize speech` span

`play audio` span

`store call recording` span

Failure-only spans

`process channel message` span

`compose event` span

How to read attribute tables