Discussions

I have a really cool "Proof of Concept" app to help you learn French I did with new bilingual MS voices. Its RAG model with Langchain and ChatGPT featuring French lessons. You can do some neat Chat roleplay with the Avatar teacher etc. Code is done and its ready for me to do the Video. I'll do that tomorrow and I will share the code and the Video links here on D-ID for reference.  [block:image] { "images": [ { "image": [ "https://files.readme.io/3b3fd55-image.png", null, null ], "align": "center", "border": true } ] } [/block]

Hi, I am an overseas Chinese and want to use API to develop some product ideas. In the process, I need to use Chinese. Does streaming WebRTC now support Chinese voice?

When using the streaming API, what is the returned video size of the webRTC stream, and is there a way to specify the returned video size?

Hi, I'm doing some tests using your streams api, I would like to change the example face and voice, how can I choose an image to animate and the voice of the playing audio? Is there a list to choose from? Thanks in advance.

D-ID community members - sharing a video on how to use D-ID with ChatGPT and Langchain to build Customer Service Agents to let your clients do Q&A with your FAQ docs off your support pages: Here you go (Code included): <https://youtu.be/KhYjGOzMcFw?si=tlHVSxFZk7Z91FxN> 

This software just keeps impressing me... So innovative and so much fun to creat with... Love the new credit model. This video has long format responses... used 9 credits to make this. I cannot wait to try a roleplay with this and some multi-language chats. Here you go ---code freely shared on GitHub via link in the show notes of the video. Please star the repo if you use it. If you're not subscribed to the YouTube channel please consider it as does not cost a thing and helps me reach the community. <https://www.youtube.com/watch?v=YtLgVdyFN_I&t=165s>  

Does the real-time avatar API support multiple sessions? Or is there only one session for one API key?

Hello, I am interested in creating my own AI avatar with my voice. My goal is to instruct the chatbot about my personal information, provide it with a backstory, and ensure that it can answer questions about me and my life. Could you please confirm whether this is achievable using your D-ID tools? I am considering purchasing the premium package to begin constructing my AI chatbot and deploy it on my website using your API Thank you. Chris

Hello, I'm facing an issue with streaming where I need to capture the event when a video stops playing in order to hide and reveal the video for the user on front-end. How can I achieve this?

Hi im trying to upload an audio file from elevenlabs (because you dont support the new v2 multilingual model for other languages) and then send it with the talk stream (the stream is active and connected) but i always get an 502 - Bad Gateway error, here is the error: ``` (node:15216) ExperimentalWarning: The Fetch API is an experimental feature. This feature could change at any time talk status response: Response { [Symbol(realm)]: null, [Symbol(state)]: { aborted: false, rangeRequested: false, timingAllowPassed: true, requestIncludesCredentials: true, type: 'default', status: 502, timingInfo: { startTime: 4666.184200048447, redirectStartTime: 0, redirectEndTime: 0, postRedirectStartTime: 4666.184200048447, finalServiceWorkerStartTime: 0, finalNetworkResponseStartTime: 0, finalNetworkRequestStartTime: 0, endTime: 0, encodedBodySize: 36, decodedBodySize: 36, finalConnectionTimingInfo: null }, cacheState: '', statusText: 'Bad Gateway', headersList: HeadersList { [Symbol(headers map)]: [Map], [Symbol(headers map sorted)]: null }, urlList: [ [URL] ], body: { stream: undefined } }, [Symbol(headers)]: HeadersList { [Symbol(headers map)]: Map(8) { 'date' => 'Sun, 29 Oct 2023 13:29:29 GMT', 'content-type' => 'application/json', 'content-length' => '36', 'connection' => 'keep-alive', 'x-amzn-requestid' => '14ccad85-0271-4925-b1e0-655e1e393d0b', 'x-amzn-errortype' => 'InternalServerErrorException', 'x-amz-apigw-id' => 'NkOpGGNevHcEqsg=', 'x-amzn-trace-id' => 'Root=1-653e5e39-6cc763730644319b5e6f6d8f' }, [Symbol(headers map sorted)]: null } } ``` I tried then to use your audio upload from the api reference and there surprisendly i get an success, but still i used that audio_url i got and send it with the talk Stream and still get an 502 - Bad Gateway. Wierdly before it was a 400 - bad Request but with the same code from your doc. Here is the api request code: ``` console.log(req.file) const audioFile = req.file const { streamId, sessionId, message } = req.body const formData = new FormData() formData.append('source_url', audioFile.path) formData.append('audio', createReadStream(audioFile.path)) try { const audioUpload = await fetch('https://api.d-id.com/audios', { method: 'POST', headers: { Authorization: `Basic ${process.env.DID_API_KEY}`, // accept: 'application/json', // 'Content-Type': 'multipart/form-data' }, body: formData, }) console.log(audioUpload) const uploadJSON = await audioUpload.json() const talkResponse = await fetchWithRetries(`${process.env.DID_URL}/talks/streams/${streamId}`, { method: 'POST', headers: { Authorization: `Basic ${process.env.DID_API_KEY}`, accept: 'application/json', 'Content-Type': 'application/json', }, body: JSON.stringify({ script: { type: 'audio', // audio_url: 'https://d-id-public-bucket.s3.us-west-2.amazonaws.com/webrtc.mp3', audio_url: uploadJSON.url // audio_url: "s3://d-id-audios-prod/auth0|653563f5966d0e4e974a038f/KXe7fZQKkoxXO-bdOj9Fo/elevenLabsAudio.wav", }, config: { stitch: true, }, // session_id: sessionId, }), }); console.log('talk status response: ', talkResponse) } catch (error) { console.log(error) res.status(500).json({output: 'An Error appeared on talkToStream Route.', error: error}) } }; ``` The Audio should not be the problem because it worked on your site. I tried to use normal node fetch and your api, to talk to the stream but still same result. I noticed when i wanted to use your api for audio upload (api.uploadAnAudio()) i get an error that this doesnt exist on the api. Just wanted to mention that. I tried to use your talk to Stream api reference on the page but even there i get an 502 Bad gateway. But there i couldnt remove the provider in the script object, so i dont know if that was a reason. I hope you can help me.