Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Amazon Nova 2 Sonic / Nova 2.5 Sonic (Bedrock) Amazon Web Services | Gemini Live API (Gemini Developer API / Google AI Studio) Google | Gemini Live API on Vertex AI (Gemini Enterprise Agent Platform) Google Cloud | |
|---|---|---|---|
| Category | Voice-to-voice | Voice-to-voice | Voice-to-voice |
| Status | GA | GA | GA |
| Est. per minute | $0.022 - 0.12 | $0.022 - 0.12 | $0.022 - 0.12 |
| How that was worked out | UNVERIFIED token rate. Assuming ~25 speech tokens/s (community figure): low = 1 min user speech (1,500 x $3/1M) + 1 min model speech (1,500 x $12/1M) = $0.0225, single turn. High uses the same 10 minute, 50 turn model as other providers and assumes history is re-processed each turn like other S2S APIs (AWS does not document this). Third-party sites quote roughly $0.015/min. | Low = gemini-3.8-live, 1 min user audio (1,500 tokens x $3/1M) + 1 min model audio (1,500 tokens x $12/1M), single turn. High = a 10 minute call with 50 turns (6 s of user audio + 6 s of model audio per turn, 500-token text system prompt), where the full conversation history is re-billed as input on every turn with no cache hits, total divided by 10 minutes. Live models do not support context caching, so there is no cached discount. Video input or thinking tokens add more. | Low = 1 min user audio + 1 min model audio at $3 / $12 per 1M, single turn. High = a 10 minute call with 50 turns (6 s of user audio + 6 s of model audio per turn, 500-token text system prompt), where the full conversation history is re-billed as input on every turn with no cache hits, total divided by 10 minutes. Google states tokens from past turns are re-processed and billed every turn up to the context window limit. Live avatar video adds about $0.37 per minute of avatar speech. |
| Pricing model | per-token | per-token | per-token |
| Free tier | None specific to Nova Sonic (AWS Free Tier credits may apply to new accounts). | Yes: free tier for all Live models with lower rate limits; free-tier content may be used to improve Google products. | No Live-specific free tier; standard Google Cloud new-customer credits apply. |
| Connects by | HTTP/2 bidirectional (InvokeModelWithBidirectionalStream) | WebSocket | WebSocket |
| Audio in | audio/lpcm 16-bit mono at 8, 16 or 24 kHz, base64 in audioInput events (~32 ms frames streamed in real time). | Raw 16-bit PCM little-endian, natively 16 kHz (other rates resampled if the MIME type says so, e.g. audio/pcm;rate=16000). Images/video as JPEG or PNG frames, max 1 fps. | Raw 16-bit PCM 16 kHz little-endian; JPEG images/video at 1 fps; text. |
| Audio out | audio/lpcm 16-bit mono at 8, 16 or 24 kHz, base64 audioOutput events. | Raw 16-bit PCM little-endian at 24 kHz (always). | Raw 16-bit PCM 24 kHz little-endian; text; mp4 video for live avatars. |
| Languages | English (US, UK, India, Australia), French, Italian, German, Spanish, Portuguese, Hindi, with automatic language detection and switching. | Live guide lists 99 languages (overview page says 70); native audio models pick the language automatically and do not accept a language code. | Vertex overview states 24 languages for multilingual support (Developer API docs claim more); verify per language. |
| Latency (vendor claim) | Vendor claim: March 2026 refresh cut user-perceived p50 latency by 150 ms; Nova 2.5 Sonic claimed lower latency than Nova 2 Sonic (no absolute numbers published). | No numeric vendor claim found. | No numeric vendor claim found. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Bedrock data is not used to train models and stays in the chosen Region (in-Region inference only). Bedrock is HIPAA eligible and covered by AWS SOC reports; confirm Nova Sonic is listed in your BAA scope. | Paid tier data is not used to improve products; free tier is. No BAA or data residency on the Developer API; use Vertex AI for enterprise compliance (CMEK, VPC-SC, regional processing). | Google Cloud terms; CMEK in us/eu multi-regions; customer data not used for training under Google Cloud terms. HIPAA BAA available for covered Google Cloud services (confirm Live API coverage). |
| Self-hostable | No | No | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| Flat $/min | - | - | - |
| Audio in $/1M tok | $3 | $3 | $3 |
| Audio out $/1M tok | $12 | $12 | $12 |
| Free tier | No | Yes | No |
| Free credit $ | - | - | - |
| Native S2S | Yes | Yes | Yes |
| Tools | Yes | Yes | Yes |
| Image in | - | Yes | Yes |
| Own LLM | No | No | No |
| Voices | 16 | 30 | 30 |
| Cloning | - | - | - |
| Latency ms | - | - | - |
| Languages | 7 | 99 | 24 |
| Context tokens | 1,000,000 | 131,072 | 128,000 |
| Max session min | 8 | 10 | 10 |
| Concurrency | 20 | - | 1,000 |
| WebRTC | No | No | No |
| WebSocket | No | Yes | Yes |
| Phone / SIP | No | No | No |
| HIPAA | Yes | No | Yes |
| SOC 2 | Yes | - | - |
| EU data | Yes | No | Yes |
| Open weights | No | No | No |
| High warnings | 2 | 3 | 2 |