Compare realtime APIs

Pick up to four APIs from any category and see them side by side.

bitHuman
bitHuman
Roboflow Serverless Video Streaming (WebRTC)
Roboflow
Gemini Live API (video input)
Google
CategoryAvatars + videoAvatars + videoAvatars + video
StatusGABetaPreview
Est. per minute$0.02 - 0.10$0.005 - 0.20$0.002 - 0.0042
How that was worked outCredit rates at the $1 = 100 credits top-up price: self-hosted $0.02, cloud $0.04, all-inclusive voice $0.10CPU 0.1 credit/h at $2.86 = $0.005/min; GPU large 2 credits/h at $6 = $0.20/min; GPU medium $0.05-$0.10/minVideo input only. Low = Google's listed $0.002/min; high = our arithmetic at 1 fps x 70 tokens x 60 s = 4,200 tokens at $1/M. Audio is billed on top.
Pricing modelcreditscreditsper-minute
Free tierFree plan: 99 credits, 1 concurrent cloud session, chat with featured avatars; page says API access on Free only 'until 12 October'.Free plan includes 10 credits per month (about 10 hours of GPU-medium streaming).See Gemini API free tier (not checked here).
Connects byLiveKit, WebRTCWebRTCWebSocket
Audio inAudio from your agent/TTS (or bitHuman managed voice chat)NonePCM audio
Audio outYour TTS or managed voiceNoneNative audio
LanguagesLanguage-agnostic lip sync from audio (not explicitly verified).n/aSee voice segment.
Latency (vendor claim)No latency number published; CPU benchmark shows 1.2x to 2.4x real-time rendering on an Intel i7-13700F.Quality and FPS can take up to a minute to ramp up at 1080p30 (vendor docs).See voice segment.
Key limits
  • Concurrent cloud sessions: 1 / 3 / 10 / 50 / 200 by plan
  • Self-hosted sessions not concurrency-limited on Creator+ (per page)
  • A session needs network at start; offline only for up to 5 minutes
  • 10 concurrent streams per workspace by default
  • Billing starts when the serverless function spawns and WebRTC connects
  • Streams stop with HTTP 402 when credits run out
  • Max 1 frame per second
  • Audio plus video sessions limited to 2 minutes unless you use session management/compression
  • Context window 128k tokens for native audio models
High-severity warnings
  • Free API access has an end date
  • Self-hosted is not offline-licensed
  • Streams die at zero credits
  • 2 minute cap with video
ComplianceVendor states usage reports contain no audio, video, images or conversation text.Not verified in this pass.Google Cloud / Gemini API terms; see voice segment.
Self-hostableYesYesNo
Last checked2026-10-102026-10-102026-10-10
Key numbers and features
Session $/min$0.02$0.005$0.002
Entry plan $/mo$20$39$0
Free tierYesYes-
Free credit $$0.99--
Custom avatarYes--
From photoYes--
Own LLMYes--
Own voiceYes--
Interrupts---
Resolution p1,080--
FPS--1
CPU onlyYesYes-
Latency ms---
Languages---
Max session min--2
Concurrency310-
WebRTCYesYes-
WebSocket--Yes
Phone / SIP---
HIPAA---
SOC 2---
EU data---
Self-hostYesYesNo
Open weightsNoYesNo
High warnings211