Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| AssemblyAI Voice Agent API AssemblyAI | xAI Grok Voice Agent API xAI | ElevenAgents (formerly Conversational AI / Agents Platform) ElevenLabs | |
|---|---|---|---|
| Category | Voice-to-voice | Voice-to-voice | Voice-to-voice |
| Status | GA | GA | GA |
| Est. per minute | $0.075 | $0.08 | $0.08 - 0.13 |
| How that was worked out | Flat all-inclusive rate; telephony not included. | Flat $0.08 per minute on grok-voice-think-fast-2.0 regardless of context length. Tool calls and text inputs are extra. xAI does not state whether minutes are session wall-clock time or audio time, so assume wall-clock time including silence. | $0.08 platform rate plus LLM pass-through; a third-party guide puts LLM at about $0.0005/min (GPT-5 Nano) to $0.045/min (GPT-5.5). Telephony and burst pricing extra. |
| Pricing model | per-minute | per-minute | per-minute |
| Free tier | $50 free credits at signup, no card. | None documented for the voice agent. | 15 call minutes per month, 4 concurrent calls. |
| Connects by | WebSocket | WebSocket | WebSocket, SIP, Twilio, Web/mobile SDKs, Embeddable widget |
| Audio in | PCM16 mono 24 kHz (audio/pcm default) | audio/pcm at 8000, 16000, 22050, 24000 (default), 32000, 44100 or 48000 Hz; audio/pcmu, audio/pcma (G.711); audio/opus. JSON base64 or binary transport. | pcm_8000/16000/22050/24000/44100/48000 or ulaw_8000 (negotiated per agent) |
| Audio out | PCM16 24 kHz (reply.audio) | Same format options as input; speed 0.7 to 1.5. | Same enum as input |
| Languages | Declared via input.language_codes or auto-detected. | Docs say every voice can speak every supported language; TTS lists 20 languages and STT 38+. No explicit list for the voice agent. | Docs give both '31 languages' and '70+ languages' for the voice layer (inconsistent). |
| Latency (vendor claim) | Not stated on the pages read. | Vendor claim: sub-second latency. | Described as low-latency; no figure on the overview page. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Vendor describes the API as PCI-certified; other certifications not re-verified. | xAI states SOC 2 Type II, HIPAA eligible with a BAA, GDPR with EU data residency options, and that audio is never stored or used for training (vendor claims). | Enterprise: DPA/SLA, BAA for HIPAA, custom SSO; regional data residency hosts (EU, India, Singapore). SOC 2/GDPR not re-verified this session. |
| Self-hostable | No | No | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| Flat $/min | $0.075 | $0.08 | $0.08 |
| Audio in $/1M tok | - | - | - |
| Audio out $/1M tok | - | - | - |
| Free tier | Yes | No | Yes |
| Free credit $ | $50 | - | - |
| Native S2S | No | Yes | No |
| Tools | Yes | Yes | Yes |
| Image in | - | - | - |
| Own LLM | - | No | Yes |
| Voices | - | - | 5,000 |
| Cloning | - | Yes | Yes |
| Latency ms | - | - | - |
| Languages | - | - | 31 |
| Context tokens | - | - | - |
| Max session min | - | - | - |
| Concurrency | - | - | 6 |
| WebRTC | No | No | - |
| WebSocket | Yes | Yes | Yes |
| Phone / SIP | No | No | Yes |
| HIPAA | - | Yes | Yes |
| SOC 2 | - | Yes | - |
| EU data | - | Yes | Yes |
| Open weights | No | No | No |
| High warnings | 0 | 1 | 2 |