Commit Graph

9290 Commits

Author SHA1 Message Date
Aleix Conchillo Flaqué
25dcf7def6 PipelineTask: add on_frame_reached_upstream/on_frame_reached_downstream 2025-03-13 10:26:11 -07:00
Filipi Fuchter
30432639b4 Creating a keep alive connection 2025-03-13 14:20:25 -03:00
Adnan Siddiquei
1bf964a667 Added two examples on how to use Neuphonic as a TTS (07u). 2025-03-13 14:42:42 +00:00
Adnan Siddiquei
08fb931ef6 Swapped NEUPHONIC_API_TOKEN for NEUPHONIC_API_KEY. 2025-03-13 12:10:03 +00:00
Aleix Conchillo Flaqué
c5aa931096 Merge pull request #1358 from pipecat-ai/aleix/abstractmethod-fixes
ai_services: fix abstractmethod issues
2025-03-12 17:26:48 -07:00
Filipi Fuchter
d33a4b3a11 Implementing reconnection logic. 2025-03-12 18:23:12 -03:00
Filipi Fuchter
9cad8bfcc6 Increasing the time that we are waiting for the frame. 2025-03-12 15:36:40 -03:00
Mark Backman
b084a3e9e7 Merge pull request #1367 from MaCaki/macaki/rime/send_msg_in_flush_audio
[rime client] Sending over trailing space to help indicate end of utt…
2025-03-12 14:25:18 -04:00
macaki
5c9e33bc7a formatting 2025-03-12 12:20:18 -06:00
Filipi Fuchter
93d8ddf4f2 Only showing the timout warning to receive frame if the client is connected. 2025-03-12 15:13:59 -03:00
Adnan Siddiquei
0b9c4b2255 Fixed a couple of small bugs. 2025-03-12 18:04:48 +00:00
macaki
effb5f6cd8 added changelog 2025-03-12 11:57:25 -06:00
Adnan Siddiquei
ead555eb4b Corrected versions on pyproject.toml. 2025-03-12 17:39:04 +00:00
macaki
f843482968 [rime client] Sending over trailing space to help indicate end of utterance after a punctuation. 2025-03-12 11:26:43 -06:00
Adnan Siddiquei
23a4933af9 Initial implementation of Neuphonic service. A TTS provider. 2025-03-12 17:15:31 +00:00
Filipi Fuchter
0d05312071 Supporting renegotiation inside the voice agent server. 2025-03-12 11:55:38 -03:00
Filipi Fuchter
f8e33d8b7b Improving the video transform feedback when we are connecting, and cleaning the pc_id when disconnected. 2025-03-12 11:49:33 -03:00
Filipi Fuchter
f24c5b0aa7 Adding support for renegotiation. 2025-03-12 11:31:18 -03:00
Michael Louis
d9ef19233a Added foundational example for ultravox 2025-03-12 10:30:23 -04:00
Mark Backman
357334e3c9 Merge pull request #1341 from pipecat-ai/mb/fix-google-typo
Add a set_language convenience method for GoogleSTTService
2025-03-12 09:05:52 -04:00
Filipi Fuchter
da25e0c008 Configuring the bot to receive the video live. 2025-03-12 10:00:33 -03:00
Filipi Fuchter
c99d02d8bb Adding support for interruptions when using SmallWebRTCTransport. 2025-03-12 09:09:11 -03:00
Mark Backman
59ea94af86 Merge pull request #1360 from pipecat-ai/mb/update-cartesia-voice
Update Cartesia voice for demos
2025-03-12 08:02:26 -04:00
Mark Backman
4a363bebf0 Add a set_language convenience method for GoogleSTTService 2025-03-12 07:58:29 -04:00
Mark Backman
c196fb5f98 Merge pull request #1342 from pipecat-ai/mb/lmnt-flush-audio 2025-03-11 22:22:38 -04:00
Mark Backman
5f97f6ff94 Add flush_audio() to LmntTTSService 2025-03-11 21:57:54 -04:00
Mark Backman
5860fe5319 Merge pull request #1340 from pipecat-ai/mb/fish-flush
Add flush_audio to FishTTSService
2025-03-11 21:56:44 -04:00
Mark Backman
3522bbb533 tmp 2025-03-11 21:55:18 -04:00
Mark Backman
cfca7269f4 Update the Cartesia voice in all demos with one built for sonic-2 2025-03-11 21:53:03 -04:00
Mark Backman
e6f269a903 Add flush_audio to FishTTSService 2025-03-11 21:48:41 -04:00
Mark Backman
468e936a5f Merge pull request #1356 from pipecat-ai/mb/add-chirp-tts-support
Add support for Chirp voices in GoogleTTSService
2025-03-11 20:12:52 -04:00
Lucas Rothman
ecc4411128 Tavus support for custom output rate 2025-03-11 16:02:33 -07:00
Aleix Conchillo Flaqué
740ba4e759 ai_services: fix abstractmethod issues 2025-03-11 14:29:03 -07:00
Filipi Fuchter
e56c8f881c Full video transformation example using SmallWebRTCTransport. 2025-03-11 11:36:47 -03:00
Filipi Fuchter
a747f08017 Simple voice agent example using SmallWebRTCTransport. 2025-03-11 11:36:23 -03:00
Filipi Fuchter
c6c0b73345 P2P WebRTC transport option to Pipecat: SmallWebRTCTransport. 2025-03-11 11:35:39 -03:00
Filipi Fuchter
fde90ee01d Creating an EventEmitter util class 2025-03-11 11:33:47 -03:00
Filipi Fuchter
689a844aaf Created a new transport param to inform if the camera input should be enabled. 2025-03-11 11:33:24 -03:00
Filipi Fuchter
aab98b61a0 Fixed issue where sending too many images per second caused Gemini to ignore them. 2025-03-11 11:32:38 -03:00
Mark Backman
a62741df94 Add support for Chirp voices in GoogleTTSService 2025-03-11 07:56:27 -04:00
Mark Backman
5bd359ada9 Merge pull request #1354 from pipecat-ai/mb/cartesia-changelog
Changelog entry for Cartesia model update
2025-03-11 07:20:04 -04:00
Mark Backman
40562402a2 Changelog entry for Cartesia model update 2025-03-10 21:10:11 -04:00
Mark Backman
98e5089fbe Merge pull request #1353 from kunal-cai/main
[Cartesia] Update the default alias for Cartesia TTS Service
2025-03-10 21:07:19 -04:00
Kunal Shah
e1c8a09b60 [Cartesia] Update the default alias for Cartesia TTS Service 2025-03-10 14:43:58 -07:00
Filipi da Silva Fuchter
154fe65011 Merge pull request #1336 from pipecat-ai/fixing_function_calling_examples
Pipecat small fixes and refactored function calling examples
2025-03-07 16:10:27 -03:00
Mark Backman
61f534ca34 Merge pull request #1334 from pipecat-ai/aleix/user-and-bot-turn-audio
add support for user and bot turn audio
2025-03-06 18:35:56 -05:00
Mark Backman
a91c26785f Store recording in a folder 2025-03-06 18:31:48 -05:00
Aleix Conchillo Flaqué
d7e93551d2 examples(chatbot-audio-recording): add support for user/bot turn audio 2025-03-06 11:49:01 -08:00
Aleix Conchillo Flaqué
06c742a2ad AudioBufferProcessor: add on_user_turn_audio_data and on_bot_turn_audio_data 2025-03-06 11:49:01 -08:00
Filipi Fuchter
55b0797fd5 Removing the extra examples inside the unified-format-function-calling folder 2025-03-06 12:00:22 -03:00