Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Google Cloud Speech-to-Text V2 streaming (Chirp 3) Google Cloud | Smallest.ai Pulse STT Smallest AI | Deepgram Nova-3 and Flux (streaming) Deepgram | |
|---|---|---|---|
| Category | Speech-to-text | Speech-to-text | Speech-to-text |
| Status | GA | GA | GA |
| Est. per minute | $0.004 - 0.016 | $0.004 - 0.006 | $0.0042 - 0.0098 |
| How that was worked out | V2 tiered price; most teams pay $0.016/min until 500K minutes per month. Multi-channel audio is billed per channel. | Changelog $0.006/min is the newest first-party figure; older page $0.004/min. | Low = Nova-3 mono on Growth; high = Flux Multilingual PAYG ($0.0078) + diarization ($0.0020) where supported. Add-ons stack. |
| Pricing model | per-minute | per-minute | per-minute |
| Free tier | V1 includes 60 free minutes/month; new Google Cloud accounts get $300 trial credit (Google Cloud free program). | Not captured. | $200 free credit for new accounts, does not expire until used (pricing page). |
| Connects by | gRPC | WebSocket | WebSocket |
| Audio in | ExplicitDecodingConfig (LINEAR16, MULAW, ALAW and others) with sample rate and channel count, or auto-decoding for containers. Audio must be sent at roughly real-time pace. | See realtime quickstart (formats not captured in this pass). | Raw linear16, linear32, mulaw, alaw, opus, ogg-opus need encoding + sample_rate (8000, 16000, 24000, 44100, 48000 listed for Flux); containerized WAV/Ogg/WebM can be sent without those params. Flux strongly recommends 80 ms chunks (2560 bytes at 16 kHz linear16). |
| Audio out | n/a | n/a | n/a |
| Languages | Chirp 3 table lists about 111 locales (my count: 29 GA, 82 Preview). | Streaming: en, hi, de, es, ru, it, fr, nl, pt, zh, yue, ja, ko, gu, mr, or, bn, ta, te, kn, ml plus regional auto-detect groups (north_indic, multi-asian, multi-south-indic). East Asian languages US region only; South Indian languages India region only (beta). | Nova-3: multilingual code-switching mode for 10 languages plus a long list of single-language codes (see Models and Languages page). Flux: English, or 10 languages with flux-general-multi. |
| Latency (vendor claim) | No vendor figure captured. | See Pulse model card (not captured). | Vendor claim: Flux end-of-turn detection around 260 ms. No published latency figure for Nova-3 found in this pass. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Google Cloud compliance programs (HIPAA BAA via Google Cloud, etc.) apply per Google's covered-services list; data logging opt-in affects V1 pricing. Not re-verified per model. | Zero data retention documented for Enterprise plans. | Vendor markets HIPAA (BAA) and SOC 2 and offers self-hosted/on-prem deployment; not re-verified in this pass, confirm with sales. |
| Self-hostable | No | No | Yes |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/hour | $0.96 | $0.36 | $0.288 |
| Bills silence | - | - | - |
| Free tier | Yes | - | Yes |
| Free credit $ | $300 | - | $200 |
| Live speakers | No | Yes | Yes |
| Turn detect | - | Yes | Yes |
| Keyterms | Yes | - | Yes |
| PII redact | - | Yes | Yes |
| Partials | - | Yes | Yes |
| Mixed langs | - | - | Yes |
| 8 kHz phone | Yes | - | Yes |
| Latency ms | - | - | 260 |
| Languages | - | 21 | 59 |
| Max session min | 5 | - | - |
| Concurrency | - | - | 150 |
| WebRTC | No | No | No |
| WebSocket | No | Yes | Yes |
| gRPC | Yes | No | No |
| HIPAA | Yes | - | Yes |
| SOC 2 | - | - | Yes |
| EU data | Yes | No | Yes |
| Self-host | No | No | Yes |
| Open weights | No | No | No |
| High warnings | 2 | 0 | 2 |