6 Pull requests merged by 3 people

• Pipecat small fixes and refactored function calling examples

  #1336 merged Mar 7, 2025

• add support for user and bot turn audio

  #1334 merged Mar 6, 2025

• introduce BaseObject class

  #1332 merged Mar 5, 2025

• Updated example to switch pipelines per the original request

  #1320 merged Mar 5, 2025

• Unified format for function calling

  #1211 merged Mar 5, 2025

• pyproject: update pyht to 0.1.12

  #1330 merged Mar 5, 2025

7 Pull requests opened by 4 people

• Added ultravox service

  #1331 opened Mar 4, 2025

• Add flush_audio to FishTTSService

  #1340 opened Mar 7, 2025

• Fix: Correct name for set_language in GoogleSTTService

  #1341 opened Mar 7, 2025

• Add flush_audio() to LmntTTSService

  #1342 opened Mar 7, 2025

• Add a Pipecat Cloud deployment example

  #1343 opened Mar 7, 2025

• Call Transfer demo

  #1348 opened Mar 9, 2025

• [Cartesia] Update the default alias for Cartesia TTS Service

  #1353 opened Mar 10, 2025

2 Issues closed by 2 people

• Gemini Quota | Whats the alternative to get the transcription?

  #1345 closed Mar 10, 2025

• PlayHTTTSService - error generating TTS: AsyncClient.tts() got an unexpected keyword argument 'protocol' since 0.0.58

  #1309 closed Mar 5, 2025

12 Issues opened by 7 people

• LiteLLM SDK LLM Service

  #1352 opened Mar 10, 2025

• Incorrect Import in documention for OpenAI Realtime Beta Usage Examples

  #1351 opened Mar 10, 2025

• Human Client (sending mic input and playback received audio) for conversation with bot running on a WebSocket-server

  #1350 opened Mar 10, 2025

• Only Conversational Flow

  #1349 opened Mar 10, 2025

• Short user utterances cause Gemini errors (No turn to complete) and connection closing

  #1347 opened Mar 9, 2025

• Infinite error recursion in daily.py

  #1346 opened Mar 9, 2025

• Gemini Multimodal context mangling

  #1344 opened Mar 7, 2025

• Elevenlabs TTS with word timing

  #1339 opened Mar 6, 2025

• BaseOutputTransport bug when using audio mixer

  #1338 opened Mar 6, 2025

• Add support for Google Chirp3 voices

  #1337 opened Mar 6, 2025

• Simplify the testing process

  #1335 opened Mar 6, 2025

• Allow TTS filters to return empty text

  #1333 opened Mar 5, 2025

14 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Adding dify support

  #378 commented on Mar 9, 2025 • 1 new comment

• P2P WebRTC transport option to Pipecat

  #1290 commented on Mar 10, 2025 • 1 new comment

• handle emails in end of sentence matching

  #1304 commented on Mar 6, 2025 • 1 new comment

• Daily Bot Does Not Leave Room After Sending EndFrame

  #1236 commented on Mar 4, 2025 • 0 new comments

• Inifinite exception recursion with 0.56 using Google LLM

  #1170 commented on Mar 6, 2025 • 0 new comments

• 1 sec. extra latency added since v.0.0.57

  #1319 commented on Mar 10, 2025 • 0 new comments

• ImportError: cannot import name 'InterruptibleTTSService' from 'pipecat.services.ai_services' [pipecat-ai 0.0.58]

  #1314 commented on Mar 10, 2025 • 0 new comments

• Support for Phi 4 Multimodal

  #1316 commented on Mar 10, 2025 • 0 new comments

• 'DeepgramSTTService' object has no attribute 'sample_rate'

  #1315 commented on Mar 10, 2025 • 0 new comments

• Options to pass through frames (transcription, llm context, etc...)

  #1322 commented on Mar 10, 2025 • 0 new comments

• [Bug] Unable to select virtual speaker device

  #1164 commented on Mar 10, 2025 • 0 new comments

• Frame reordering breaks interrupts and causes bot to repeat itself multiple times

  #1323 commented on Mar 10, 2025 • 0 new comments

• adding langfuse for openai

  #847 commented on Mar 10, 2025 • 0 new comments

• Fix overlapping audio issue in AudioBufferProcessor

  #1325 commented on Mar 4, 2025 • 0 new comments