Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Deepgram Nova-3 and Flux (streaming) Deepgram | Gladia Live (Solaria-1) Gladia | Google Cloud Speech-to-Text V2 streaming (Chirp 3) Google Cloud | |
|---|---|---|---|
| Category | Speech-to-text | Speech-to-text | Speech-to-text |
| Status | GA | GA | GA |
| Est. per minute | $0.0042 - 0.0098 | $0.0042 - 0.013 | $0.004 - 0.016 |
| How that was worked out | Low = Nova-3 mono on Growth; high = Flux Multilingual PAYG ($0.0078) + diarization ($0.0020) where supported. Add-ons stack. | $0.25/hr Growth floor to $0.75/hr Starter. | V2 tiered price; most teams pay $0.016/min until 500K minutes per month. Multi-channel audio is billed per channel. |
| Pricing model | per-minute | per-hour | per-minute |
| Free tier | $200 free credit for new accounts, does not expire until used (pricing page). | One-time EUR 50 credit (vendor estimates 60+ realtime hours); does not renew. | V1 includes 60 free minutes/month; new Google Cloud accounts get $300 trial credit (Google Cloud free program). |
| Connects by | WebSocket | WebSocket | gRPC |
| Audio in | 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). | Declare encoding (e.g. wav/pcm), sample_rate, bit_depth and channels at session init; they must match the chunks you send. Multi-channel supported. | 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. |
| Audio out | n/a | n/a | n/a |
| Languages | 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. | 100+ with code-switching (Solaria-1). | Chirp 3 table lists about 111 locales (my count: 29 GA, 82 Preview). |
| Latency (vendor claim) | Vendor claim: Flux end-of-turn detection around 260 ms. No published latency figure for Nova-3 found in this pass. | No vendor latency number captured in this pass. | No vendor figure captured. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Vendor markets HIPAA (BAA) and SOC 2 and offers self-hosted/on-prem deployment; not re-verified in this pass, confirm with sales. | Default retention: paid 3 weeks for audio/transcripts, 1 year metadata; Enterprise custom or zero retention. Certifications not re-verified. | 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. |
| Self-hostable | Yes | No | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/hour | $0.288 | $0.75 | $0.96 |
| Bills silence | - | - | - |
| Free tier | Yes | Yes | Yes |
| Free credit $ | $200 | - | $300 |
| Live speakers | Yes | - | No |
| Turn detect | Yes | Yes | - |
| Keyterms | Yes | Yes | Yes |
| PII redact | Yes | - | - |
| Partials | Yes | Yes | - |
| Mixed langs | Yes | Yes | - |
| 8 kHz phone | Yes | - | Yes |
| Latency ms | 260 | - | - |
| Languages | 59 | 100 | - |
| Max session min | - | 180 | 5 |
| Concurrency | 150 | 30 | - |
| WebRTC | No | No | No |
| WebSocket | Yes | Yes | No |
| gRPC | No | No | Yes |
| HIPAA | Yes | - | Yes |
| SOC 2 | Yes | - | - |
| EU data | Yes | - | Yes |
| Self-host | Yes | No | No |
| Open weights | No | No | No |
| High warnings | 2 | 1 | 2 |