Stream Video & Audio + Vision Agents
Stream's managed WebRTC edge network for video/audio calls, plus Vision Agents, an open-source (Apache-2.0) Python framework for voice and video AI agents that uses Stream as its default transport.
Overview
Best for: In-app voice/video agents, especially with vision (camera) input.
At a glance
Fee is $0.30 per 1,000 participant minutes for agent plus one user. Noise cancellation and recording are paid add-ons. HIPAA via sales. No telephony.
WebRTC
WebRTC
Depends on providers.
No verified number.
Global edge (not detailed).
HIPAA: contact sales (per pricing page). Others not verified.
Features
- noise cancellation (add-on)
- recording
- transcription/captions (add-on)
- multi-provider plug-ins (Vision Agents)
- video processors (e.g. YOLO pose)
Pricing
| What | Price | Unit |
|---|---|---|
| Audio participant minutes (calls) | $0.30 | per 1,000 participant minutes |
| Noise cancellation | $0.30 | per 1,000 participant minutes |
| Transcription / closed captions | $8.00 | per 1,000 call minutes |
| Audio recording | $1.50 | per 1,000 call minutes |
Transport is about $0.0006/min for agent + user; the rest is your STT/LLM/TTS or realtime model bill from providers. Not a vendor figure.
Free tier: $100 free credits (Build).
Source: getstream.io
Setup
- Create a Stream app (API key + secret).
- uv add "vision-agents[getstream, openai, elevenlabs, deepgram]".
- Define an Agent with edge=getstream.Edge(), an agent_user, instructions and an llm (or STT/LLM/TTS), then have it join a Stream call your client app opens.
Endpoint
Stream Video APIAuthentication
STREAM_API_KEY / STREAM_API_SECRET; provider keys
Quick start python
# Vision Agents (shape from the GitHub README example; see README for the full runnable file)
# uv add "vision-agents[getstream, openai]"
from vision_agents.core import Agent, User # verify import path in README
from vision_agents.plugins import getstream, openai
agent = Agent(
edge=getstream.Edge(),
agent_user=User(name="Assistant"),
instructions="You are a friendly voice assistant. Keep replies short.",
llm=openai.Realtime(), # or separate stt=..., llm=..., tts=...
)
# Then create/join a Stream call from your app and have the agent join it.Written from the current docs. Check the vendor's SDK version before you ship.
Warnings
Transport is cheap, models are not
Stream's audio rate is a fraction of a cent per minute; nearly all cost is the AI providers you plug in.
Snippet imports not verified
README only shows a partial example; check the docs for exact import paths and the call-join helper.
No telephony
Stream is a WebRTC network; phone agents need a separate SIP/PSTN provider.
Captions billed per call minute
Transcription add-on is $8 per 1,000 call minutes, separate from any STT you run for the agent.
Plus 12 warnings that apply to all platforms and telephony APIs. See category warnings.
Limits
- No PSTN in sources reviewed
- HIPAA via sales
Models and products
| Name | Status |
|---|---|
| Build (free) | GA |
| Pay-as-you-go | GA |
| Vision Agents (open source) | GA |
Docs and sources
Docs
Sources used
Vision Agents import paths and join API; regions; SOC 2.