Commit Graph

8500 Commits

Author SHA1 Message Date
filipi87
02cfb129d3 Invoke cleanup method on VAD analyzer. 2026-03-24 10:49:14 -03:00
filipi87
311afef7da Fixing Krisp Viva example. 2026-03-24 10:48:22 -03:00
Filipi da Silva Fuchter
5ed183d215 Merge pull request #4022 from krispai/krisp-viva-vad-support
Draft Implementation for Krisp VIVA VAD.
2026-03-24 09:44:32 -04:00
Mark Backman
5c3d3aea2b Merge pull request #4115 from pipecat-ai/mb/user-turn-stop-warnings
Warn when VAD stop_secs misconfiguration may degrade turn detection
2026-03-24 09:32:20 -04:00
Mark Backman
0651569a4e Merge pull request #4119 from Alex-wuhu/novita-integration
feat: add Novita AI as LLM provider
2026-03-24 09:30:05 -04:00
Mark Backman
bf04ea2043 Add changelog for #4119 2026-03-24 09:23:40 -04:00
Mark Backman
aa0b49d69f Code review fixes 2026-03-24 09:22:08 -04:00
Alex-wuhu
8c6f4a8d7b Add Novita AI LLM service provider 2026-03-24 09:20:50 -04:00
Mark Backman
bbaa5971c4 Merge pull request #3981 from dhruvladia-sarvam/feat/sarvam-llm-integration
Sarvam LLM Integration
2026-03-24 09:00:01 -04:00
Mark Backman
cdd8c3e5bb Fix examples 2026-03-24 08:53:56 -04:00
Mark Backman
1c8a8f51d4 Code review fixes 2026-03-24 08:46:03 -04:00
dhruvladia-sarvam
349b8645f3 Merge branch 'main' into feat/sarvam-llm-integration 2026-03-24 16:34:12 +05:30
dhruvladia-sarvam
696196e30c alignment with pr 4081 2026-03-24 16:29:58 +05:30
Garegin Harutyunyan
dacffccd3a fixed runtime issue. 2026-03-24 12:56:19 +04:00
Aleix Conchillo Flaqué
7414b30308 Merge pull request #4116 from pipecat-ai/changelog-0.0.107
Release 0.0.107 - Changelog Update
v0.0.107
2026-03-23 20:13:49 -07:00
aconchillo
3268cb93d5 Update changelog for version 0.0.107 2026-03-23 20:11:31 -07:00
Aleix Conchillo Flaque
9211379720 update uv.lock 2026-03-23 20:06:28 -07:00
Mark Backman
42cab7eea0 Add changelog entry for #4115 2026-03-23 18:01:04 -04:00
Mark Backman
483b643b07 Warn when VAD stop_secs misconfiguration may degrade turn detection
Add warnings in SpeechTimeoutUserTurnStopStrategy and
TurnAnalyzerUserTurnStopStrategy when stop_secs differs from the
recommended default (0.2s) or when stop_secs >= STT p99 latency,
which collapses the STT wait timeout to 0s. Document the stop_secs=0.2
assumption in stt_latency.py.
2026-03-23 17:57:51 -04:00
Filipi da Silva Fuchter
12dc429761 Merge pull request #4104 from pipecat-ai/filipi/audio_issue
Allow defining whether to insert silence in the output transport.
2026-03-23 17:17:37 -04:00
filipi87
066b206b3d Renaming insert_silence to auto_silence 2026-03-23 18:12:26 -03:00
filipi87
ddd1b71b56 Renaming audio_out_insert_silence to audio_out_auto_silence 2026-03-23 17:57:42 -03:00
filipi87
8612c9f50a Updating to use daily-python 0.27.0 2026-03-23 17:52:41 -03:00
Mark Backman
fd0bfe141f Merge pull request #4109 from pipecat-ai/pk/tiny-fix 2026-03-23 15:17:19 -04:00
filipi87
3042929989 Fixing changelog description. 2026-03-23 15:57:25 -03:00
dhruvladia-sarvam
0f6cc231cf removing error wraps and model validation check 2026-03-24 00:06:15 +05:30
dhruvladia-sarvam
3428a4c6ad fixes post PR 4081 2026-03-23 23:45:27 +05:30
Mark Backman
f283cc5bc6 Merge pull request #4091 from pipecat-ai/mb/gradium-multiplexing-setup
feat: send per-context setup in Gradium TTS multiplexing
2026-03-23 12:00:53 -04:00
Mark Backman
70552d7697 Add changelog entry for #4091 2026-03-23 11:58:14 -04:00
Mark Backman
84c2a24c9f feat: send per-context setup messages in Gradium TTS multiplexing
Send a setup message with client_req_id before the first text message
for each context, matching Gradium multiplexing protocol. This allows
Gradium to associate each session with its setup configuration when
using close_ws_on_eos=False.
2026-03-23 11:58:14 -04:00
Garegin Harutyunyan
f8c7414ea7 format fix. 2026-03-23 18:58:19 +04:00
Garegin Harutyunyan
f1f51de962 Merge branch 'main' into krisp-viva-vad-support 2026-03-23 18:35:58 +04:00
Paul Kompfner
e93b0ace06 Remove an unnecessary check in SyncParallelPipeline 2026-03-23 10:00:32 -04:00
Garegin Harutyunyan
c32240e14b Fixed review comments. 2026-03-23 17:44:48 +04:00
filipi87
e6602f9244 Disabling auto_silence for tavus video service. 2026-03-22 18:28:57 -03:00
filipi87
9a30b18f21 Configuring Daily CustomAudioSource to automatically inject silence or not. 2026-03-22 17:29:01 -03:00
filipi87
936a39f4a1 Updating tavus examples to not send silence. 2026-03-22 14:41:23 -03:00
filipi87
3b1cb30926 Adding changelog entry. 2026-03-22 13:26:00 -03:00
filipi87
ce36487143 Allow defining whether to insert silence in the output transport. 2026-03-22 13:09:09 -03:00
Mark Backman
ec3bd8c5b1 Merge pull request #4097 from pipecat-ai/mb/update-minimax-docs-link
Update MiniMaxHttpTTSService platform docs link
2026-03-21 07:08:40 -04:00
Mark Backman
622ebd5d74 Update MiniMaxHttpTTSService platform docs link 2026-03-21 07:02:06 -04:00
Mark Backman
a9a1941a45 Merge pull request #4093 from poislagarde/fix/genesys-pong-parameters 2026-03-20 19:52:58 -04:00
Pablo Ois Lagarde
53e0136366 chore: rename changelog fragment to PR #4093
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 16:46:35 -03:00
Pablo Ois Lagarde
bc0e7130b8 fix: always include parameters field in Genesys AudioHook messages
The AudioHook protocol requires every message to carry a `parameters`
object. `_create_message` conditionally included it only when parameters
were truthy, so pong responses and closed responses without
outputVariables were sent without the field.

Clients that validate message structure (including the Genesys reference
implementation) rejected these messages, which broke server sequence
tracking and prevented outputVariables from reaching the Architect flow.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 16:37:53 -03:00
Mark Backman
d8af4447ff Merge pull request #3449 from kingster/telemetry-fix-system-message
fix: Record correct system_instruction in LLM spans for LLM services
2026-03-20 13:42:47 -04:00
Mark Backman
c89e366739 refactor: align tracing attributes with OpenTelemetry GenAI conventions
- gen_ai.system -> gen_ai.provider.name (deprecated)
- system / system_instructions -> gen_ai.system_instructions
- gen_ai.usage.cache_read_input_tokens -> gen_ai.usage.cache_read.input_tokens
- gen_ai.usage.cache_creation_input_tokens -> gen_ai.usage.cache_creation.input_tokens
2026-03-20 13:36:20 -04:00
Mark Backman
b5c362d6e6 refactor: rename tracing span attribute "system" to "system_instructions"
Align with the OpenTelemetry GenAI semantic convention
gen_ai.system_instructions for system prompts. The old "system"
attribute name was unrelated to gen_ai.system (which is for
provider name).
2026-03-20 13:20:03 -04:00
Mark Backman
e5aaa4c4eb fix: read system_instruction from _settings instead of removed attribute
Replace adapter-based extraction in traced_llm with direct reads from
_settings.system_instruction (priority) and context messages (fallback).
The old approach had three bugs: signature mismatch with Anthropic
adapter, key name inconsistency, and unnecessary overhead from full
message/tools conversion.

Also deduplicate the system instruction in spans -- it was appearing as
both "system" and "param.system_instruction".
2026-03-20 13:12:40 -04:00
Varun Singh
a12ad27348 enable_dialout should not depend on sip_caller_phone being set (#4087)
* enable_dialout should not depend on SIP being set

* we still need room_prefix to have pipecat-sip, s/sip/telephony in room prefix
2026-03-20 10:01:31 -07:00
Mark Backman
44504efdc7 Merge pull request #4090 from pipecat-ai/mb/fix-tts-audio-context-routing
fix: route TTS audio through audio context queue in Fish, LMNT, Neuph…
2026-03-20 11:06:53 -04:00