Discussions

this is my code const options = { method: 'POST', url: '<https://api.d-id.com/talks/streams'>, headers: {accept: 'application/json', 'content-type': 'application/json',"Authorization": `Basic ${DID_TOKEN_ONE}`}, data: { face: {top_left: [0, 0], size: 512}, config: {motion_factor: 0, align_expand_factor: 0, stitch: true}, source_url: '<https://i.ibb.co/RYKFZF0/rdj-avatar.jpg'>, // driver_url: 'string' } }; console.log("hey"); const response = await axios.request(options); console.log("response fetched", response.satus); res.status(200).json(response.data); } catch(error){ console.log(error); res.status(333).json(error); } and this is the output I got: { "message": "Request failed with status code 500", "name": "AxiosError", "stack": "AxiosError: Request failed with status code 500\\n at settle (/home/mohammed/Documents/explore_next_js/node_modules/axios/dist/node/axios.cjs:1913:12)\\n at IncomingMessage.handleStreamEnd (/home/mohammed/Documents/explore_next_js/node_modules/axios/dist/node/axios.cjs:2995:11)\\n at IncomingMessage.emit (node:events:525:35)\\n at endReadableNT (node:internal/streams/readable:1359:12)\\n at process.processTicksAndRejections (node:internal/process/task_queues:82:21)", "config": { "transitional": { "silentJSONParsing": true, "forcedJSONParsing": true, "clarifyTimeoutError": false }, "adapter": [ "xhr", "http" ], "transformRequest": [ null ], "transformResponse": [ null ], "timeout": 0, "xsrfCookieName": "XSRF-TOKEN", "xsrfHeaderName": "X-XSRF-TOKEN", "maxContentLength": -1, "maxBodyLength": -1, "env": {}, "headers": { "Accept": "application/json", "Content-Type": "application/json", "Authorization": "Basic cm9uaWRpZDU2MUBnbWFpbC5jb20:WgE_GKuEnUBZekSRhxfPD", "User-Agent": "axios/1.5.1", "Content-Length": "160", "Accept-Encoding": "gzip, compress, deflate, br" }, "method": "post", "url": "<https://api.d-id.com/talks/streams">, "data": "{\"face\":{\"top_left\":[0,0],\"size\":512},\"config\":{\"motion_factor\":0,\"align_expand_factor\":0,\"stitch\":true},\"source_url\":\"<https://i.ibb.co/RYKFZF0/rdj-avatar.jpg\"}"> }, "code": "ERR_BAD_RESPONSE", "status": 500 }

Hi - I’ve been working on integrating a custom stream/talk in my WebApp. I’ve followed the docs and the sample app on GitHub. chrome://WebRTC-Internals tells me the signals are successful. However, when I review the stream stats, it’s telling me 0 bytes. It is streaming but it doesn’t look like a video is being streamed. Is it possible to do some debugging together? I did notice in the talk api….the sample docs didn’t mention a source_url…but the api responded with an error saying it was required. I wasn’t sure what it needed so I sent the url of the image & it seems to take the params I’m sending and respond successfully.

I am soooo close --- it integrates with ChatGPT and it streams back my answers but its just the Voice portion that is generated and it does not give me the animated avatar -- just shows the pic. See on right the answer -- I asked it what was capital of New York? It replied The capital of new your is Albany... It gave me the audio stream but the image did not animate... It did swap over from the idle Loop to the still and then went back to idle looping... that works... But in never animated the still image when it streamed the voice response... I thought the voice and video streams were coming off the video file so confused... Ideas? I can post the code but its 300 lines and beast to look at... Anyone seen this? 

Trying the streaming talk demo from github, Unable to replace/remove the current figure from the demo and replace with another. How is this accomplished in the demo code? Once the start button clicked, new image appears, but disappears when audio ends, replace with the male roman.

Hi there, I am trying to integrate your streaming feature for my application but I am facing the problem now. Following the API reference steps, I am testing your API but to start a stream endpoint shows 500 error. What is the problem? I have also tried to execute your github reference source code but the result was same. Please provide me solution to use your streaming service. Thanks,

In D-ID AI stream I am trying to access the live stream avatar but I am facing ERROR for the below program import requests url = "<https://api.d-id.com/talks/streams/id/ice"> payload = { "candidate": "[{'foundation': '2', 'protocol': 'udp', 'priority': 1679819007, 'ip': '35.89.173.93', 'port': 31940, 'type': 'srflx'}, {'foundation': '1', 'protocol': 'udp', 'priority': 2015363327, 'ip': '35.89.173.93', 'port': 31940, 'type': 'host'}]", "sdpMid": "audio", "sdpMLineIndex": 0 } headers = { "accept": "application/json", "content-type": "application/json", "authorization": "Basic c2F0ZWVzaEBzdWphaW5mby5jb206U3VqYUAxMjM=" } response = requests.post(url, json=payload, headers=headers) print(response.text) i am facing this error {"message": "Internal server error"} i have given all correct details but still i am facing error

I want to create a talking news anchor by connecting a newsfeed - such as Google News, webz or the like to D-ID avatar. Is this possible? Also if possible is there a way to make it intermittent - example, 6pm newscast, 8am news cast and so on. Lastly, if this is possible can I make a newscast of my Facebook feed? Twitter, etc.. I am not a programmer I just think your software is awesome and it made me think of the possibilities. Here is newscast I created and then put on FB but I wanted to be able to do it automatically for my town(i believe they have api) and other towns to get away from humdrum text: <https://www.facebook.com/rbschoolcraft/videos/962432114824260> Thanks, Robert Schoolcraft

I would like to inquire about how the usage of WebRTC stream APIs affects the consumption of credits. Does it calculate based on the duration of the WebRTC session or the time it takes to generate the speech? Either way, according to my calculations, a basic chatbot session would cost approximately $0.6 to $2.5. This ongoing cost is not feasible for many scenarios. For instance, we are developing a mental health chatbot solution and while we love and appreciate the D-ID stream solution, we are unable to afford the ongoing cost for our clients. It poses a challenge for us. Thanks

I want to connect a real time avatar to my API. My API returns an answer that the avatar should read. Step by step, how can I configurate this? I will add a text box on the button of the avatar, so the user can write questions.

On <https://docs.d-id.com/reference/createstream> you mention face_id parameter. What is it referring to? Also, is it possible to create a stream via API using one of the AI presenters that show up in D-ID studio under Generate AI Presenter? (as opposed to submitting a photo of your own)?