So, its been a long process and a lot of work - literally re-writing our voice orchestration to be native - and we still have a small sprint before we will start flowing traffic that way. Here is just a general guide of somethings that will change, be added and be deprecated. So, rollout. first - the users using our numbers will start seeing the traffic flow first. Then older numbers. Then trunked numbers. Nothing tangible changes from your perspective besides lower latency. Tooling - So, we are adding POST / GET / PUT / PATCH / DELETE to api request types. We also have it where you can configure headers, query parameters, path parameters and body parameters. So, fully customized API calls. We will suppose variables in these as well so you can pass API keys or your access token for GHL. Here's the thing, tools is now running through a proxy of ours that will open up the doors for a couple things: - Tools to run as they do today - Direct API calls (will be a toggle), so instead of being wrapped in a args object with metadata, etc - we will just send the API call. This gets rid of the need for middleware because you can make direct API calls. - Workflow execution; not today or the next week but we are adding native workflows to the platform. You can configure a custom tool to trigger a workflow locally to run multi-agent frameworks and basic automation so we will support a middleware internally. Abilities - all stays the same, but we are adding agent teams in voice (chat following right after). So, add different assistants into call to create a team env on the call either through a "prompt change" so we just change the prompt dynamically, or through a team so mutliple voices, etc. AI Models - We will be running a custom fine-tuned model thats been fine-tuned for voice orchestration. aka, this llm outputs text-to-speech friendly output to keep weird translations to a minimum. You will be able to select an OpenAI model if you would like and run it with your key if you prefer OpenAI output.

So, when using your own openai key (and even us as a business), you notice with agent stack (tools, prompt, convo history, RAG, etc) it starts to stack up quick - especially if you have a really involved process. We implemented a token optimization model before our chat completions to ensure you get the cost savings and ill share some data at the end :) So, we are now truncating and summarizing conversation history - we noticed there are large chat completeions coming through with 300-400+ message histories. This becomes expensive overtime if its a lead you've been working or following up with for a while engaging in conversation, so we are reducing that number and summarizing the history to ensure the intelligence stays the same but the token consumption goes way down (98% decrease on larger runs) Another thing we are doing is truncating large tool call outputs within the window that are not relevant to the current task - meaning, if there are tool calls with large outputs (like get_availability), if they are not relevant to the current task at hand, we truncate the response to show the agent that the action happened but the context is shorter. This saw a huge reduction in token consuption as well (96% decrease on larger runs) Here is the before and after, this is the same exact conversation history, assistant ID, tools, custom fields, knowledge base, etc - but see the speed and cost difference and the output was the exact same message: Differences: - 35 seconds faster - 95.95% cheaper ---- Before: "error_type": null, "usage_cost": { "notes": null, "tokens": { "output": 211, "input_total": 175948, "input_cached": 0, "input_noncached": 175948 }, "total_cost": 0.353584, "model_normalized": "gpt-4o", "models_encountered": [ "gpt-4o" ], "price_used_per_million": { "input": 2.5, "cached_input": 1.25, "output": 10 }, "error_message": null, "run_time_seconds": 32.692, "returned_an_error": false, After: "run_time_seconds": 2.618, "returned_an_error": false,

Would yall want to pass your own 11labs key for your own voices / acct for voice? would obviously drop price for input keys but curious would anyone use this before I built it / move on

I just discovered an issue. I’ve tested and the Transfer Call custom tool works fine to land lines, cell phones, but not to a business VOIP line. Here’s the background: Our client has an Assistable agent that books appointments, etc. If a caller is upset or specifically requests to speak with a human we’re calling a transfer call customer tool to redirect to their front desk. After testing against half a dozen numbers - different types (landline, cell, and VOIP), carriers, times, DND mode settings of the receiving line, and answering/voicemail set or not - the only time it’s failing is when the call attempts to direct to a VOIP line. @Jorden Williams @Mike Copeland is this a known issue and is there a workaround?

So, saw some stuff come in about duplicate / double messages coming through - started as just FB but it seems like meta and custom conversation providers (whatsapp etc). Triaged it to find there was a timeout-retry happening for wait times & / or large tool stacks - the server would think the request is taking too long and try again only to find out that the request was just finishing up. I added a proxy before the chat completion run which allows us to queue the run so this never happens again :) let me know if you see different, happy monday