Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Amazon Transcribe Streaming (incl. Medical and Call Analytics) AWS | Azure AI Speech real-time speech to text Microsoft | ElevenLabs Scribe v2 Realtime ElevenLabs | |
|---|---|---|---|
| Category | Speech-to-text | Speech-to-text | Speech-to-text |
| Status | GA | GA | GA |
| Est. per minute | $0.01 - 0.075 | $0.0067 - 0.025 | $0.0065 - 0.0098 |
| How that was worked out | $0.01/min standard streaming up to $0.075/min Medical. Add PII redaction or CLM as needed. | $0.40/hr commitment-tier overage up to $1.20/hr custom + $0.30/hr add-on. Pay-as-you-go standard is $0.0167/min. | $0.39/hr base to $0.59/hr with keyterms + editing. |
| Pricing model | per-minute | per-hour | per-hour |
| Free tier | 60 minutes per month for 12 months from first request (excludes PII redaction). | F0: 5 audio hours per month shared between standard and custom real-time; 1 concurrent request. | Free plan includes about 2.5 realtime hours. |
| Connects by | HTTP/2, WebSocket | WebSocket (via Speech SDK), REST for short audio | WebSocket |
| Audio in | PCM signed 16-bit little-endian (not WAV), FLAC, or Opus in Ogg. 16 kHz recommended; 8 kHz telephony accepted. Chunks of 50-200 ms recommended; send zero-byte silence rather than pausing. | Speech SDK handles microphone, files and push/pull streams; default 16 kHz 16-bit mono PCM; compressed formats via GStreamer. | audio_format: pcm_8000, pcm_16000 (default), pcm_22050, pcm_24000, pcm_44100, pcm_48000, ulaw_8000; audio sent base64 in JSON input_audio_chunk messages. |
| Audio out | n/a | n/a | n/a |
| Languages | Many streaming languages (count not re-verified); Medical is US English. | 100+ locales (see language support page; count not re-verified). | 90+ languages (vendor); language_code plus secondary_languages hints. |
| Latency (vendor claim) | No vendor figure captured; latency depends on chunk size per docs. | No vendor figure captured. | Vendor claim: ~150 ms (footnoted, conditions not stated). |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Amazon Transcribe and Transcribe Medical are HIPAA-eligible under the AWS BAA per AWS (not re-verified here). AI services opt-out policy controls data use for training. | Azure compliance scope (HIPAA BAA, SOC, ISO) applies to Azure AI Speech per Microsoft; connected/disconnected containers available. Not re-verified. | Data-residency hosts for EU, India, Singapore; enable_logging=false for zero retention. Certifications not re-verified. |
| Self-hostable | No | Yes | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/hour | $0.6 | $1 | $0.39 |
| Bills silence | Yes | - | - |
| Free tier | Yes | Yes | Yes |
| Free credit $ | - | - | - |
| Live speakers | Yes | Yes | - |
| Turn detect | - | - | Yes |
| Keyterms | Yes | Yes | Yes |
| PII redact | Yes | - | - |
| Partials | Yes | Yes | Yes |
| Mixed langs | - | Yes | - |
| 8 kHz phone | No | - | Yes |
| Latency ms | - | - | 150 |
| Languages | 77 | - | 90 |
| Max session min | - | - | - |
| Concurrency | 25 | 100 | 9 |
| WebRTC | No | No | No |
| WebSocket | Yes | Yes | Yes |
| gRPC | No | No | No |
| HIPAA | Yes | Yes | - |
| SOC 2 | - | Yes | - |
| EU data | Yes | Yes | Yes |
| Self-host | No | Yes | No |
| Open weights | No | No | No |
| High warnings | 1 | 1 | 0 |