Discussions

estou a querer inserir um ficheiro de jpg de uma imagem e nao estou a conseguir, o que posso fazer?

import requests url = "<https://api.d-id.com/talks"> payload = { "script": { "type": "text", "subtitles": "false", "provider": { "type": "elevenlabs", "voice_id": "21m00Tcm4TlvDq8ikWAM" }, "input": "This is an AI prompt that works using python" }, "config": { "fluent": "false", "pad_audio": "0.0" }, "source_url": "<https://img.freepik.com/free-photo/handsome-bearded-guy-posing-against-white-wall_273609-20597.jpg?t=st=1714185052~exp=1714185652~hmac=383a21b3bb15d52279d7caa61d64112ec02ff373e4036e14c3c65288ab05935f"> } headers = { "accept": "application/json", "content-type": "application/json", "authorization": f"Basic (My API key" # Replace YOUR_API_KEY_HERE with your actual API key } response = requests.post(url, json=payload, headers=headers) print(response.text) <br> I am unsure how to implement the API key or username and password, I am getting a link to visit but I am receiving a "Unauthorized" message on that link. {"id":"tlk_arJeT_tnWlwWwBv9S91E6","created_at":"2024-04-27T03:09:41.261Z","created_by":"google-oauth2|118274173746624624115","status":"created","object":"talk"}

<br> I'm currently working with a video editing API for my project, and I'm looking to implement seamless transitions between video clips. I have custom audio tracks prepared for each clip, and each audio track includes 1-second silence at the start and end to ensure smooth blending between the clips. I'm wondering if the Clips API supports this feature, or if there are any plans for it to be supported in future updates like in the Talks API with the fluent setting. Thank you in advanced. <br>

Hi, how can I change a presenter after generating the video? I am new to the system and have just mistakenly used 22 credit on the wrong presenter. Thank you.

hello

Tell me how to create video <br>

Hi, I want to generate a video where the character is not talking. I've used several stopwatches in the script and when it generates the video, it says it's generating a 7s video but the final video is 0s. How can I generate video with movement but no speech?

Occasionally, the streaming video and audio may experience interruptions during playback, which could be due to issues with the WebRTC connection i guess? Are there methods available to optimize this and prevent the video from breaking?

We use D-ID Studio with German language output. Unfortunately, all English words within the German text are pronounced in German as well, which sounds very awkward. Is there a possibility to mark those words within the German text which should be pronounced in English? In html one can, for example, use a language tag to make screenreaders pronounce English words properly.

If I set the logo to anything, I get a "400 bad request", I am using axios and am trying to create options like this: const options = { method: 'POST', headers: { accept: 'application/json', 'content-type': 'application/json', authorization: `Bearer ${bearer}` }, data: JSON.stringify({ config: { logo: { url: "ai", position: [ 0, 0 ] }, stitch: true, result_format: 'mp4' }, source_url, driver_url: `bank://${driver_url}` }) };