Commit graph

21 commits

Author SHA1 Message Date
Chris Briddock
20617db37a
Add Open AI Comatible API option in model configuration
Add unit tests for various UI components and context hooks

- Created tests for Progress, RadioGroup, Select, Separator, Sheet, Sidebar, Skeleton, Sonner, Switch, Table, Tabs, Textarea, Tooltip components.
- Implemented tests for UserConfigContext and other context hooks.
- Added utility tests for filters and utils functions.
- Set up MSW for API mocking in tests.
- Configured Vitest for testing environment with necessary setup.
2026-05-25 19:26:41 +01:00
Abhishek
3892b58486
feat: add ultravox realtime and fix signature issue in telephony (#345)
* feat: add ultravox realtime and fix signature issue in telephony

- Add UltraVox realtime
- Fix signature issue on telephony

* fix: fix regression for wss_backend_endpoint
2026-05-23 12:51:55 +05:30
Abhishek Kumar
9135c2da13 feat: add xai grok as realtime model 2026-05-22 18:04:59 +05:30
Octopus
0e0d3136ca
feat: add MiniMax provider support (Chat + TTS) (#309)
* feat: add MiniMax provider support (Chat + TTS)

- Add MiniMax LLM provider using OpenAI-compatible API
  - Models: MiniMax-M2.7, MiniMax-M2.7-highspeed
  - Default base URL: https://api.minimax.io/v1
  - Uses MINIMAX_API_KEY for authentication
- Add MiniMax TTS provider using Pipecat's MiniMaxHttpTTSService
  - Models: speech-2.8-hd (default), speech-2.8-turbo
  - 6 built-in voices
  - Requires group_id configuration
- Add unit tests for both providers

* fix(minimax): validator, temperature, session cleanup, reasoning filter
  - check_validity.py: wire MiniMax into _validator_map and enforce
    group_id at save time. Without this, saving a config with a valid
    key was rejected.
  - registry.py: surface temperature on the LLM config (gt=0; MiniMax
    rejects 0) and base_url on the TTS config
  - service_factory.py:
    * Plumb temperature through create_llm_service
    * Normalize TTS base_url to include /t2a_v2 — pipecat appends only
      ?GroupId=... to the URL.
    * Use the new MiniMaxLLMService (from pipecat) to strip
      <think>...</think> reasoning that MiniMax-M2.7 emits inline in
      delta.content (otherwise it leaks straight to TTS).
    * Use MiniMaxOwnedSessionTTSService so the per-instance aiohttp
      session gets closed in cleanup() instead of leaking sockets/FDs.
  - minimax_tts.py: small wrapper around MiniMaxHttpTTSService that owns
    the session it was handed (pipecat's caller-owns-session API
    conflicts with the ftory's per-instance pattern).
  - pipecat submodule: bumps to a commit that adds MiniMaxLLMService — a
    thin OpenAILLMService subclass with the streaming <think> filter
    (mirrors NvidiaLLMService's pattern for NIM reasoning models).
  - Tests updated/added for all of the above.

  Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: octo-patch <octo-patch@github.com>
Co-authored-by: Sabiha Khan <sabihak89@gmail.com>
2026-05-22 13:09:41 +05:30
Abhishek
2381a803ad
feat: add openai realtime models (#298)
* feat: add openai realtime models

* chore: bump pipecat

* fix: resample telephony audio for openai realtime

* fix: sampling rate fix for openai realtime

* chore: clean up dead code
2026-05-16 18:05:23 +05:30
Abhishek Kumar
e255b33813 feat: add Rime TTS 2026-04-07 14:05:47 +05:30
Abhishek Kumar
c4c4b591db feat: add gladia stt support 2026-04-04 14:47:48 +05:30
Abhishek Kumar
501d06c00d feat: add Assembly AI STT 2026-04-03 07:10:37 +05:30
Abhishek
87e72d5f6f
feat: add gemini live and speaches integration (#220)
* feat: add speaches models

* feat: add gemini realtime and speaches integration

- Add gemini realtime support
- Add speaches support for locally hosted LLMs

* chore: bump pipecat

* feat: add language option

* fix: add skip aggregator types to tts settings

* fix: make API key optional for realtime
2026-03-31 21:42:03 +05:30
Abhishek Kumar
83f05ab146 fix: send auth credentials with validate service keys 2026-03-27 00:07:38 +05:30
Abhishek Kumar
ac0731a374 feat: add support for self hosted llm models 2026-03-24 17:50:45 +05:30
neil from camb.ai
31e075d114
feat: add CAMB AI TTS integration (#187)
Co-authored-by: Abhishek <abhishek@a6k.me>
2026-03-24 12:54:07 +05:30
Abhishek Kumar
fe84f086ba feat: add AWS Bedrock support 2026-03-19 15:06:59 +05:30
Abhishek
494c60d774
feat: add hybrid text + recording functionality in agents (#191)
* feat: add recording feature in agents

* chore: pin pipecat version

* feat: show usage in UI

* chore: update pipecat
2026-03-16 15:04:08 +05:30
Abhishek Kumar
e34e4f8f3c chore: upgrade pipecat 2026-03-06 16:49:14 +05:30
Abhishek Kumar
4c936ae57d feat: add openrouter support 2026-02-09 13:31:32 +05:30
Abhishek
ef5b9e40a9
feat: knowledge base functionality for the voice agent (#120)
* feat: upload file and store embedding

* feat: add documents in nodes

* feat: add openai embedding service
2026-01-17 14:37:03 +05:30
Abhishek Kumar
11e033c72d fix: formatting fix and fix #79
Improve Safari Permissions UX
2026-01-12 12:47:32 +05:30
Abhishek
edf0fa4fbc
fix: migrate from custom audio recorder to native AudioBuffer (#115)
* fix: update to pipecat VM Detector

* fix: refactor to remove audio synchronizer

* feat: add speechmatics as STT
2026-01-08 18:03:26 +05:30
Abhishek
45c5b7c304
feat: add voice selectors in elevenlabs (#88) 2025-12-25 15:05:53 +05:30
Abhishek Kumar
4f2a629340 Initial Commit 🚀 🚀 2025-09-09 14:37:32 +05:30