D-ID API
Generate talking head videos and real-time avatar conversations through an API
- Tool type
- Generative video and avatar API
- Made for
- Developers and product teams
- Runs on
- Hosted API and browser embedding
- Requests are sent to D-ID's hosted API; the web studio is used for account and video creation, and agents can be embedded in websites via client keys.
What it does
D-ID's API takes a still image of a face, or a video, combined with a script as text or an audio file, and returns a video of a digital presenter speaking. Developers send a request with parameters such as the image, script and voice settings. D-ID's real-time option also streams avatar video for live conversations using WebRTC.
Teams use the API to add personalized presenter videos to training, marketing and support content, to translate existing videos into new languages with lip-sync, or to place a talking avatar inside a chatbot or video call. The real-time agent path lets developers combine an avatar with an LLM and a knowledge base uploaded for retrieval-augmented answers, and an embeddable UI can deploy agents on a website without backend code.
The API suits developers building video or conversational avatar features into products. Access requires an API key generated from the account page, and API minutes draw from the same balance as the web app. Video length is rounded up to the nearest 15 seconds, unused minutes do not roll over, and trial videos carry a full-screen watermark.
What it can do
- Generate talking head videos from a single photo and text or audio
- Create real-time streaming avatar conversations via WebRTC
- Build AI agents with custom avatars, LLM instructions and personality
- Use RAG knowledge bases uploaded as documents to ground agent responses
- Translate videos into new languages with automatic lip-sync and voice cloning
- Export conversation history as structured JSON for analytics
Works with
- LiveKit (quickstart documented)
- ElevenLabs agents (quickstart documented)
Example workflows
- Talking head video from a photo and script
- Illustrative example. Input: a face photo and a text script or audio file. Steps: send a POST request with the image, script and voice settings to the video API, then retrieve the result. Output: a rendered talking head video in the chosen language and style.
- Live avatar support agent
- Illustrative example. Input: an avatar image, LLM instructions and an uploaded knowledge base. Steps: define the agent in the Agents section, connect a session via the SDK or embed UI, and stream the conversation over WebRTC. Output: a real-time video conversation in which the avatar answers using the uploaded documents.
Before you choose
- Trial videos display a full-screen D-ID watermark, and the Trial and Lite plans show a watermark on generated videos.
- Minutes are deducted per video rounded up to the nearest 15-second interval, and unused minutes expire each month rather than carrying over.
- Free-tier accounts with no use for 6 months have their data deleted after an email notice; deleting an account removes all generated videos, agents and stored data permanently.
Listed under
Get started
Log in to D-ID, open the Account page, and generate an API key. API setup happens in the developer hub, not in a separate end-user app.
- Log in to D-ID and generate an API key from the Account page.
- Choose a path in the developer docs quickstart: Realtime agents for live conversation or Videos for asynchronous generation.
- Create an avatar or select a presenter, then send the first request using the quickstart for your chosen avatar version.
Plans and prices
Video-generation minutes use the account balance and are rounded up to 15-second intervals. Confirm current API rates, trial allowance and real-time agent charges in the API pricing table.
- Video generation and real-time avatar access
Source: d-id.com/pricing/api, checked 29 Oct 2026. Prices can change; check before you buy.
Sources for this overview
Product pages, documentation, and pricing checked 29 Oct 2026. Each source supports part of the overview; availability and prices can change.
- Generative AI API for Talking Head Video Creation | D-ID ↗www.d-id.com
- Quickstart ↗docs.d-id.com
- D-ID Pricing Plans | Generative AI Video Platform ↗www.d-id.com
- API Pricing | D-ID AI Video Generator ↗www.d-id.com
Ratings and reviews
No ratings for D-ID API yet.
What’s changed
Free accountSignals
Free accountData and security
Free accountCompare with similar tools
Free accountWhere this comes from
How we research- Company website
- d-id.com: product, pricing and policy pages
- YC directory mirror
- Batch and company name
- Social accounts
- Accounts the company links, and its posts on X
- Human review
- Checked by a person
- knowledge_base
Last checked 29 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.