Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Gemini Live API (video input) Google | Roboflow Serverless Video Streaming (WebRTC) Roboflow | bitHuman bitHuman | |
|---|---|---|---|
| Category | Avatars + video | Avatars + video | Avatars + video |
| Status | Preview | Beta | GA |
| Est. per minute | $0.002 - 0.0042 | $0.005 - 0.20 | $0.02 - 0.10 |
| How that was worked out | Video 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. | CPU 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/min | Credit rates at the $1 = 100 credits top-up price: self-hosted $0.02, cloud $0.04, all-inclusive voice $0.10 |
| Pricing model | per-minute | credits | credits |
| Free tier | See Gemini API free tier (not checked here). | Free plan includes 10 credits per month (about 10 hours of GPU-medium streaming). | Free plan: 99 credits, 1 concurrent cloud session, chat with featured avatars; page says API access on Free only 'until 12 October'. |
| Connects by | WebSocket | WebRTC | LiveKit, WebRTC |
| Audio in | PCM audio | None | Audio from your agent/TTS (or bitHuman managed voice chat) |
| Audio out | Native audio | None | Your TTS or managed voice |
| Languages | See voice segment. | n/a | Language-agnostic lip sync from audio (not explicitly verified). |
| Latency (vendor claim) | See voice segment. | Quality and FPS can take up to a minute to ramp up at 1080p30 (vendor docs). | No latency number published; CPU benchmark shows 1.2x to 2.4x real-time rendering on an Intel i7-13700F. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Google Cloud / Gemini API terms; see voice segment. | Not verified in this pass. | Vendor states usage reports contain no audio, video, images or conversation text. |
| Self-hostable | No | Yes | Yes |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| Session $/min | $0.002 | $0.005 | $0.02 |
| Entry plan $/mo | $0 | $39 | $20 |
| Free tier | - | Yes | Yes |
| Free credit $ | - | - | $0.99 |
| Custom avatar | - | - | Yes |
| From photo | - | - | Yes |
| Own LLM | - | - | Yes |
| Own voice | - | - | Yes |
| Interrupts | - | - | - |
| Resolution p | - | - | 1,080 |
| FPS | 1 | - | - |
| CPU only | - | Yes | Yes |
| Latency ms | - | - | - |
| Languages | - | - | - |
| Max session min | 2 | - | - |
| Concurrency | - | 10 | 3 |
| WebRTC | - | Yes | Yes |
| WebSocket | Yes | - | - |
| Phone / SIP | - | - | - |
| HIPAA | - | - | - |
| SOC 2 | - | - | - |
| EU data | - | - | - |
| Self-host | No | Yes | Yes |
| Open weights | No | Yes | No |
| High warnings | 1 | 1 | 2 |