The Stack · Voice, speech & video API

D-ID

Talking-avatar video API — turn a photo + text/audio into a lip-synced presenter, with real-time WebRTC streaming agents.

API keyFreemium🔵 agent: self serve instant key

Get API key → instant key, usually no card Docs Website

CategoryVoice, speech & video

TypeAPI service

Authapi-key

PricingFreemium

Agent signup🔵 self serve instant key

SDKsREST, JavaScript

Pricing: 14-day free trial (20 credits, watermark); paid from ~$4.70/mo billed annually; API access on Pro (~$49.90/mo) and up.

🔵 Agents: self serve instant key

Instant self-serve — free signup gives a key immediately (a human unblocks an agent in under 2 minutes).

Trial signup generates an API key (Basic auth) in account settings; sustained/production API use requires a paid Pro plan.

D-ID — Talking-avatar video API — turn a photo + text/audio into a lip-synced presenter, with real-time WebRTC streaming agents.
Website: https://www.d-id.com
Docs: https://docs.d-id.com
Get a key: https://studio.d-id.com
Agent signup: self serve instant key — Trial signup generates an API key (Basic auth) in account settings; sustained/production API use requires a paid Pro plan.
Auth: api-key
Pricing: freemium — 14-day free trial (20 credits, watermark); paid from ~$4.70/mo billed annually; API access on Pro (~$49.90/mo) and up.
Full record: https://dreaming.press/api/tools/d-id.json

Machine record: /api/tools/d-id.json

Quickstart

curl -X POST https://api.d-id.com/talks \
  -H "Authorization: Basic $DID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "source_url": "https://example.com/face.jpg",
    "script": {"type":"text","input":"Hello world",
               "provider":{"type":"microsoft","voice_id":"en-US-JennyNeural"}}
  }'

bash · full docs →

D-ID in our coverage

CISA's Agentic AI Security Guidance: Four of the Five Risks Have No Attacker

2026-07-08

SPIFFE for AI Agents: The Workload-Identity Problem, and the Half It Doesn't Solve

2026-07-06

China Made AI Agent Interconnection a National Standard — and Put Identity First

2026-07-04

The Agent Carries a Note It Cannot Read

2026-06-20

D-ID FAQ

What is D-ID?

D-ID is Talking-avatar video API — turn a photo + text/audio into a lip-synced presenter, with real-time WebRTC streaming agents. It's in the Voice, speech & video category of the dreaming.press tool directory.

Is D-ID free?

D-ID is freemium — free to start, paid plans for scale. 14-day free trial (20 credits, watermark); paid from ~$4.70/mo billed annually; API access on Pro (~$49.90/mo) and up..

Can an AI agent sign up for D-ID automatically?

Almost — signup is instant and self-serve (a free key with no sales call), so a human can unblock an agent in under two minutes. Trial signup generates an API key (Basic auth) in account settings; sustained/production API use requires a paid Pro plan..

Does D-ID have an MCP server?

D-ID does not publish an official MCP server as of our last check.

Is D-ID open source?

D-ID is a hosted API service, not an open-source project.

What languages does D-ID support?

D-ID offers REST, JavaScript.