Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| OpenAI Realtime transcription sessions OpenAI | Speechmatics Realtime and Agent STT Speechmatics | Rev AI Streaming Rev | |
|---|---|---|---|
| Category | Speech-to-text | Speech-to-text | Speech-to-text |
| Status | GA | GA | GA |
| Est. per minute | $0.003 - 0.017 | $0.0033 - 0.013 | $0.0033 - 0.005 |
| How that was worked out | $0.003/min (4o-mini-transcribe estimate, per turn) to $0.017/min (true streaming deltas with gpt-live-transcribe or gpt-realtime-whisper). | Linden 1 with training discount ($0.20/hr) up to Enhanced list ($0.80/hr). Subscriptions/credit packs cut up to 25%/20%. | Assumes the $0.20-$0.30/hr Reverb lines apply to streaming, which the pricing page does not confirm. |
| Pricing model | per-minute | per-hour | per-hour |
| Free tier | None specific to transcription. | $100 in credits at sign-up, no card (pricing page). | Free credits equal to 5 hours of Reverb ASR on Pay As You Go. |
| Connects by | WebSocket, WebRTC | WebSocket | WebSocket |
| Audio in | audio/pcm at 24 kHz in the documented example (16-bit, base64 in input_audio_buffer.append); G.711 formats historically supported on Realtime (not re-verified). | raw pcm_f32le, pcm_s16le or mulaw with explicit sample_rate; or 'file' type for wav, mp3, aac, ogg, mpeg, amr, m4a, mp4, flac. | content_type query param, e.g. audio/x-raw;layout=interleaved;rate=16000;format=S16LE;channels=1. Raw, FLAC or WAV recommended. |
| Audio out | n/a | n/a | n/a |
| Languages | Multilingual (count not published on the pages read); gpt-live-transcribe accepts a 'languages' hint list. | Language packs per session (vendor markets 50+ languages; count not re-verified). Enhanced/Standard need a selected language; Melia 1 handles code-switching. | language param defaults to en; streaming language list not shown on the API page. |
| Latency (vendor claim) | Vendor: 'low-latency' with tunable delay setting; no number published. | Configurable via max_delay (docs examples use 0.7 s); no other vendor latency figure captured. | No vendor figure captured. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | OpenAI API data controls apply (API data not used for training by default per OpenAI policy); BAA availability not re-verified for these models. | Docs state Realtime SaaS does not store audio, transcripts or configuration. On-prem containers and Kubernetes deployments documented. Certifications not re-verified. | Rev markets HIPAA support (site navigation lists HIPAA); not re-verified. |
| Self-hostable | No | Yes | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/hour | $1.02 | $0.45 | $0.2 |
| Bills silence | - | - | Yes |
| Free tier | No | Yes | Yes |
| Free credit $ | - | $100 | - |
| Live speakers | No | Yes | - |
| Turn detect | - | Yes | - |
| Keyterms | Yes | Yes | Yes |
| PII redact | - | - | - |
| Partials | Yes | Yes | Yes |
| Mixed langs | - | Yes | - |
| 8 kHz phone | - | Yes | - |
| Latency ms | - | - | - |
| Languages | - | 50 | - |
| Max session min | - | 2,880 | 180 |
| Concurrency | - | 50 | 10 |
| WebRTC | Yes | No | No |
| WebSocket | Yes | Yes | Yes |
| gRPC | No | No | No |
| HIPAA | - | - | Yes |
| SOC 2 | - | - | - |
| EU data | - | Yes | - |
| Self-host | No | Yes | No |
| Open weights | No | No | No |
| High warnings | 2 | 0 | 1 |