From 509a3bccde561f083f72e4f378a2d3bf5cd23af3 Mon Sep 17 00:00:00 2001 From: Elliott Chen Date: Tue, 29 Oct 2024 12:59:38 +0800 Subject: [PATCH 1/5] docs: updating wording and adding new gif wording and new gif --- README.md | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 63ddb8d5..77d8adde 100644 --- a/README.md +++ b/README.md @@ -34,28 +34,30 @@

🎉 TEN Agent with OpenAI Realtime API and RTC

-OpenAI Realtime API provides ultra-low latency, and RTC offers AI noise suppression. TEN Agent has both. Feel free to try it out at [agent.theten.ai](https://agent.theten.ai). +Combining OpenAI Realtime API for ultra-low latency with RTC’s AI noise suppression ensures smooth, high-quality interactions. On top of that, the seamless integration of weather and news tools makes TEN Agent even more versatile. Try it now at [agent.theten.ai](https://agent.theten.ai). -![TEN Agent with OpenAI Realtime API and RTC](https://github.com/TEN-framework/docs/blob/main/assets/gif/realtime-api.gif?raw=true) +![TEN Agent with OpenAI Realtime API and RTC](https://github.com/TEN-framework/docs/blob/main/assets/gif/weather-and-news.gif?raw=true)

TEN Agent Features

Aside from being world's the first agent to integrate the OpenAI Realtime API and RTC, TEN Agent also offers the following features: -1. **High-Performance Real-Time Multimodal Interactions**: +1. **OpenAI Realtime API and RTC**: TEN Agent is the world's first AI agent to integrate the OpenAI Realtime API and RTC. + +2. **High-Performance Real-Time Multimodal Interactions**: Offers high-performance, low-latency solutions for complex audio-visual AI applications. -2. **Multi-Language and Multi-Platform Support** : +3. **Multi-Language and Multi-Platform Support** : Supports extension development in C++, Go, Python, etc. Runs on Windows, Mac, Linux, and mobile devices. -3. **Edge-Cloud Integration**: +4. **Edge-Cloud Integration**: Flexibly combines edge and cloud-deployed extensions, balancing privacy, cost, and performance. -4. **Flexibility Beyond Model Limitations**: +5. **Flexibility Beyond Model Limitations**: Easily build complex AI applications through simple drag-and-drop programming, integrating audio-visual tools, databases, RAG, and more. -5. **Real-Time Agent State Management**: +6. **Real-Time Agent State Management**: Manages and adjusts agent behavior in real-time for dynamic responsiveness.
From e778fa230a5f2cf07a7415f58c8b3f749cad1358 Mon Sep 17 00:00:00 2001 From: Elliott Chen Date: Tue, 29 Oct 2024 17:43:15 +0800 Subject: [PATCH 2/5] docs: adding extensions image --- README.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/README.md b/README.md index 77d8adde..028e540e 100644 --- a/README.md +++ b/README.md @@ -60,6 +60,11 @@ Easily build complex AI applications through simple drag-and-drop programming, i 6. **Real-Time Agent State Management**: Manages and adjusts agent behavior in real-time for dynamic responsiveness. +
+

Ready-to-use Extensions

+ +![Ready-to-use Extensions](https://github.com/TEN-framework/docs/blob/main/assets/jpg/extensions.jpg?raw=true) +

Stay Tuned

From 46174c74f3428f8bf21cbfe7ee8960b040c427d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=B4=9D=E5=90=89=E5=A1=94=E5=A4=A7=E7=8E=8B?= Date: Tue, 29 Oct 2024 21:35:18 +0800 Subject: [PATCH 3/5] docs: updating the wording. --- README.md | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 028e540e..931da446 100644 --- a/README.md +++ b/README.md @@ -43,21 +43,19 @@ Combining OpenAI Realtime API for ultra-low latency with RTC’s AI noise suppre Aside from being world's the first agent to integrate the OpenAI Realtime API and RTC, TEN Agent also offers the following features: -1. **OpenAI Realtime API and RTC**: TEN Agent is the world's first AI agent to integrate the OpenAI Realtime API and RTC. - -2. **High-Performance Real-Time Multimodal Interactions**: +1. **High-Performance Real-Time Multimodal Interactions**: Offers high-performance, low-latency solutions for complex audio-visual AI applications. -3. **Multi-Language and Multi-Platform Support** : +2. **Multi-Language and Multi-Platform Support** : Supports extension development in C++, Go, Python, etc. Runs on Windows, Mac, Linux, and mobile devices. -4. **Edge-Cloud Integration**: +3. **Edge-Cloud Integration**: Flexibly combines edge and cloud-deployed extensions, balancing privacy, cost, and performance. -5. **Flexibility Beyond Model Limitations**: +4. **Flexibility Beyond Model Limitations**: Easily build complex AI applications through simple drag-and-drop programming, integrating audio-visual tools, databases, RAG, and more. -6. **Real-Time Agent State Management**: +5. **Real-Time Agent State Management**: Manages and adjusts agent behavior in real-time for dynamic responsiveness.
From 48a997eb2173cec62ba0ecf5a40e3680c29bc4e7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=B4=9D=E5=90=89=E5=A1=94=E5=A4=A7=E7=8E=8B?= Date: Wed, 13 Nov 2024 22:05:00 +0800 Subject: [PATCH 4/5] docs: Fixing the link of FishAudio Fixing the link of FishAudio --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 74c1284c..caa34bfc 100644 --- a/README.md +++ b/README.md @@ -94,7 +94,7 @@ And, if you choose to use OpenAI Realtime API, then the Vision and RAG won't be #### Keys - Agora [ App ID ](https://docs.agora.io/en/video-calling/get-started/manage-agora-account?platform=web#create-an-agora-project) and [ App Certificate ](https://docs.agora.io/en/video-calling/get-started/manage-agora-account?platform=web#create-an-agora-project)(certificate only required if enabled in the Agora Console) - [OpenAI](https://openai.com/index/openai-api/) API key -- [ Deepgram ](https://deepgram.com/) ASR and [ FishAudio ](fish.audio) TTS +- [ Deepgram ](https://deepgram.com/) ASR and [ FishAudio ](https://fish.audio/) TTS #### Installation From daf036f9299ed8df3b9cc0927c41eb5d2012f870 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=B4=9D=E5=90=89=E5=A1=94=E5=A4=A7=E7=8E=8B?= Date: Fri, 15 Nov 2024 07:31:20 +0800 Subject: [PATCH 5/5] feat: Adding Deepgram 402 condition --- .../extension/deepgram_asr_python/deepgram_wrapper.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/agents/ten_packages/extension/deepgram_asr_python/deepgram_wrapper.py b/agents/ten_packages/extension/deepgram_asr_python/deepgram_wrapper.py index fd74ae5d..bea05b71 100644 --- a/agents/ten_packages/extension/deepgram_asr_python/deepgram_wrapper.py +++ b/agents/ten_packages/extension/deepgram_asr_python/deepgram_wrapper.py @@ -80,8 +80,12 @@ async def on_error(self, error, **kwargs): interim_results=self.config.interim_results, punctuate=self.config.punctuate) # connect to websocket - if await self.deepgram_client.start(options) is False: - logger.error(f"failed to connect to deepgram") + result = await self.deepgram_client.start(options) + if result is False: + if self.deepgram_client.status_code == 402: + logger.error("Failed to connect to Deepgram - your account has run out of credits.") + else: + logger.error("Failed to connect to Deepgram") return logger.info(f"successfully connected to deepgram")