Commit Graph

794 Commits

Author SHA1 Message Date
Mark Backman
3f3d3c9203 Merge pull request #4337 from pipecat-ai/mb/fix-speech-stop-strategy
Split user-turn stop timeout into independent speech and STT timers
2026-04-22 10:23:03 -04:00
Filipi da Silva Fuchter
7858813871 Merge pull request #4270 from sathwikareddy02/nvidia-llm-update
Enhance NVIDIA LLM reasoning tokens handling and allow keyless local …
2026-04-22 10:47:54 -03:00
Mark Backman
f425e946eb Merge pull request #4349 from pipecat-ai/mb/serializer-pyright
Fix type errors in serializers and add to pyright checked set
2026-04-22 09:43:31 -04:00
Filipi da Silva Fuchter
75bd1b5b9b Merge pull request #4323 from dakshdua/daksh/allow-noninitial-whitespace-chunks
fix: when aggregating by tokens, allow inter-token whitespace once non-whitespace has been sent
2026-04-22 10:27:08 -03:00
filipi87
d953c201bd Adding changelog entry to the fix. 2026-04-22 10:24:21 -03:00
Mark Backman
263cad41f0 Add changelog for #4349 2026-04-21 18:14:15 -04:00
Mark Backman
9a49517609 Add changelog entry for #4341 2026-04-21 15:48:27 -04:00
Mark Backman
103ced1eaa Merge pull request #4347 from pipecat-ai/mb/deepgram-stt-keepalive-unbound 2026-04-21 15:15:55 -04:00
Mark Backman
648094da26 Add changelog for #4347 2026-04-21 14:51:30 -04:00
Mark Backman
b838bd906b Add changelog for #4340 2026-04-21 13:45:34 -04:00
Mark Backman
8e247f395b Merge pull request #4344 from pipecat-ai/mb/11labs-normalized-alignment 2026-04-21 13:41:04 -04:00
Mark Backman
a07bee2318 Add changelog for #4344 2026-04-21 09:12:15 -04:00
Mark Backman
2c3f051a1f Merge pull request #4325 from radhikagpt1208/fix/sentry-metrics-drop-metricsframe
Fix SentryMetrics dropping MetricsFrame from stop_ttfb/stop_processing
2026-04-21 07:57:42 -04:00
Mark Backman
9ded7bab1b Merge pull request #4334 from dhruvladia-sarvam/feat/sarvam-stt-vad-parameters-exposed
Sarvam - VAD parameters configurable on saaras:v3
2026-04-20 16:04:23 -04:00
dhruvladia-sarvam
34fb303c44 changelog descriptions 2026-04-21 00:29:38 +05:30
Mark Backman
9d8eefd2a2 Add changelog for #4337 2026-04-20 12:02:20 -04:00
Harshita Jain
03bd667f95 Fix Smallest AI TTS WebSocket endpoint URL and remove unsupported flush (#4320)
* Fix Smallest AI TTS WebSocket endpoint URL to match API documentation

Update base URL from waves-api.smallest.ai to api.smallest.ai and
fix path prefix from /api/v1/ to /waves/v1/ per the v4.0.0 docs.

* Update keepalive using silent space message instead of unsupported flush
2026-04-20 11:15:25 -04:00
sathwika
74becffe55 add changelog 2026-04-20 11:47:20 +05:30
Mark Backman
8c8b76e9d2 Merge pull request #4326 from pipecat-ai/mb/flux-multilingual 2026-04-17 15:59:11 -04:00
Mark Backman
42a6fc703c Address review feedback
- Fall back to Language.EN in _primary_detected_language when model is
  flux-general-en, preserving prior behavior on the default model.
- Standardize example on DeepgramFluxSTTService.Settings and drop the
  now-redundant DeepgramFluxSTTSettings import.
- Narrow the changed-behavior changelog to reflect that flux-general-en
  frames still carry Language.EN.
2026-04-17 15:38:14 -04:00
Mark Backman
af861b7975 Add changelog for #4326 2026-04-17 10:31:37 -04:00
Mark Backman
f5f92dea63 Add changelog entries and restore multi-line WhatsApp error log
Add changelog entries for the pyright introduction and the
LiveKitRunnerArguments.token signature tightening. Restore the
indented multi-line format for the WhatsApp missing-env error,
now listing only the vars that are actually missing.
2026-04-17 09:39:55 -04:00
Radhika Gupta
80fecab4de Fix SentryMetrics dropping MetricsFrame from stop_ttfb/stop_processing
SentryMetrics.stop_ttfb_metrics and stop_processing_metrics called the
base FrameProcessorMetrics implementation but discarded its return
value (implicit `return None`). FrameProcessorMetrics.stop_ttfb_metrics
/ stop_processing_metrics build and return a MetricsFrame, which
FrameProcessor.stop_ttfb_metrics / stop_processing_metrics then pushes
downstream so observers (e.g. UserBotLatencyObserver,
MetricsLogObserver) can see TTFB / processing metrics.

Because SentryMetrics returned None, the FrameProcessor never pushed
the MetricsFrame, so any pipeline using metrics=SentryMetrics() on STT
/ LLM / TTS services silently lost all downstream TTFB and processing
MetricsFrames. The metrics were still calculated and logged
internally, and Sentry transactions still finished correctly, but
observers never saw them.

Forward the MetricsFrame returned by the base class so FrameProcessor
can push it into the pipeline.
2026-04-17 14:48:36 +05:30
Mark Backman
7e045257e8 Merge pull request #4314 from pipecat-ai/mb/prudent-system-instruction-logging
Log system instruction once at composition time, not on every LLM call
2026-04-16 13:18:33 -04:00
Aleix Conchillo Flaqué
1c4ffb7845 Merge pull request #4313 from pipecat-ai/ac/daily-send-dtmf
Add send_dtmf() to DailyTransport
2026-04-16 08:57:48 -07:00
Aleix Conchillo Flaqué
8d4feede23 Split #4313 changelog into one entry per file 2026-04-16 08:55:03 -07:00
Aleix Conchillo Flaqué
b11a3bc43f Add method field to Daily DTMF output frames
Lets callers specify Daily's DTMF delivery method (e.g. "rfc2833"
or "info") alongside `session_id` and `digit_duration_ms`. Forwarded
to Daily's `send_dtmf` as `method`.
2026-04-16 08:55:03 -07:00
Mark Backman
686e250db1 Add changelog for #4314 2026-04-15 21:03:13 -04:00
Aleix Conchillo Flaqué
9fbe1bf2a3 Document button as a convenience shortcut, not a deprecation
The single-key `button` field on `OutputDTMFFrame` and
`OutputDTMFUrgentFrame` is kept as a first-class ergonomic shortcut
for the common single-keypress case, equivalent to
`buttons=[button]`. `buttons` takes precedence when both are set.
2026-04-15 15:09:01 -07:00
Aleix Conchillo Flaqué
d8b0e78bc8 Represent DTMF sequences as list[KeypadEntry] via buttons field
Replaces the string-based `tones` field with a type-safe
`buttons: list[KeypadEntry]` on `OutputDTMFFrame` and
`OutputDTMFUrgentFrame`, matching the existing singular `button`
field on `InputDTMFFrame`. A `from_string` classmethod builds the
list from a dial string like `"123#"` (invalid characters raise
ValueError from the `KeypadEntry` constructor).

The base output audio fallback now iterates `frame.buttons`
directly, LiveKit sends `frame.buttons[0].value`, and the Daily
transport joins the button values into the single string Daily's
`send_dtmf` expects.
2026-04-15 15:05:45 -07:00
Aleix Conchillo Flaqué
675b7df408 Add tones to OutputDTMFFrame and simplify DTMF frame hierarchy
Introduces a new `tones` field on `OutputDTMFFrame` and
`OutputDTMFUrgentFrame` for sending multi-digit DTMF sequences and
deprecates the existing single-key `button` field. When only `button`
is set, it is used as a single-character `tones` string for backward
compatibility.

`DTMFFrame` is kept as an empty marker class so both input and output
DTMF frames can still be identified via isinstance. `InputDTMFFrame`
keeps its required `button` field (single keypress semantics).

The Daily-specific `DailyOutputDTMFFrame` and
`DailyOutputDTMFUrgentFrame` frames no longer need to override
`button` and simply add `session_id` and `digit_duration_ms`, which
are forwarded to Daily's `send_dtmf` as `sessionId` and
`digitDurationMs`.

The base output audio fallback now iterates `tones` and generates a
tone per character; LiveKit's native DTMF path sends `tones[0]` since
its API is single-tone.
2026-04-15 14:48:02 -07:00
Aleix Conchillo Flaqué
30f39d7395 Add DailyOutputDTMFFrame and DailyOutputDTMFUrgentFrame
Introduces Daily-specific DTMF output frames that carry explicit
`tones`, `session_id` and `digit_duration_ms` fields, forwarded to
Daily's `send_dtmf` as `tones`, `sessionId` and `digitDurationMs`.
The inherited `button` and `transport_destination` fields are
ignored for these frames in the Daily transport.
2026-04-15 14:20:08 -07:00
Aleix Conchillo Flaqué
fe2ef9c712 Add changelog for #4313 2026-04-15 10:43:28 -07:00
filipi87
aeab417cd1 Changelogs for the STT service reconnect improvements. 2026-04-15 13:23:25 -03:00
Mark Backman
9ffcccdd84 Merge pull request #4253 from pipecat-ai/mb/mistral-stt
Add Mistral Voxtral Realtime STT service
2026-04-15 09:00:27 -04:00
Mark Backman
b834a893fe Add changelog for #4304 2026-04-14 17:52:29 -04:00
aconchillo
f8318289d4 Update changelog for version 1.0.0 2026-04-14 12:06:43 -07:00
Aleix Conchillo Flaqué
958d90819f Merge pull request #4294 from pipecat-ai/ac/fix-assistant-turn-stopped-event
Fix on_assistant_turn_stopped not firing for tool-call-only responses
2026-04-14 10:09:55 -07:00
Aleix Conchillo Flaqué
403235eb48 Add changelog for #4294 2026-04-14 10:07:19 -07:00
Mark Backman
f013d5632b Merge pull request #4293 from pipecat-ai/mb/fix-elevenlabs-tts-enable-logging
Fix ElevenLabs TTS boolean params and add missing features
2026-04-14 12:58:31 -04:00
Mark Backman
84b885682f Add changelog for #4295 2026-04-14 11:49:31 -04:00
Mark Backman
49998d252b Add changelog for #4293 2026-04-14 10:13:12 -04:00
Mark Backman
d1f7af0330 Merge pull request #4283 from pipecat-ai/mb/user-stop-transcript-improvements 2026-04-13 19:27:05 -04:00
Mark Backman
31b5a64382 Merge pull request #4282 from pipecat-ai/mb/cartesia-stt-settings-update
Reconnect Cartesia STT websocket on settings change
2026-04-13 18:18:36 -04:00
Mark Backman
d20013d7a6 Add changelog for #4283 2026-04-13 18:12:04 -04:00
Aleix Conchillo Flaqué
7dc763d512 Merge pull request #4272 from pipecat-ai/pk/llm-context-get-messages-elide-large-values
Add truncate_large_values to LLMContext.get_messages()
2026-04-13 15:04:41 -07:00
Mark Backman
36b15c92ef Add changelog for #4282 2026-04-13 17:29:39 -04:00
Filipi da Silva Fuchter
e248c4c049 Merge pull request #4249 from sathwikareddy02/nvidia-tts-update
Add stitching support and enhancements for NvidiaTTSService
2026-04-13 09:39:48 -03:00
Paul Kompfner
e38647151d Fix language: binary data is replaced with placeholders, not truncated 2026-04-11 14:39:25 -04:00
Paul Kompfner
1a02b5d61a Rename elide_large_values to truncate_large_values 2026-04-11 14:29:05 -04:00