Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Groq Whisper (no streaming) Groq | Soniox Real-time STT (stt-rt-v5) Soniox | Cartesia Ink (ink-2, ink-whisper) Cartesia | |
|---|---|---|---|
| Category | Speech-to-text | Speech-to-text | Speech-to-text |
| Status | GA | GA | GA |
| Est. per minute | $0.00067 - 0.0019 | $0.002 - 0.0025 | $0.0022 - 0.012 |
| How that was worked out | File pricing; chunking live audio into short requests raises effective cost because each request bills at least 10 s. | ~$0.12/hr vendor estimate = $0.002/min; higher with long context prompts or translation output. | ink-whisper on Scale ($0.13/hr) up to ink-2 on Pro overage (10,800 credits/hr x $65/1M = $0.70/hr). |
| Pricing model | per-hour | per-token | per-hour |
| Free tier | Groq free tier with rate limits (not detailed here). | Not stated on the pricing page. | Free plan: 20K credits/month (about 1h51m of ink-2 per plan table). |
| Connects by | HTTPS (OpenAI-compatible, file upload) | WebSocket | WebSocket |
| Audio in | flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm files or URL; 25 MB free tier / 100 MB dev tier. | audio_format 'auto' for containers, or raw PCM: pcm_s8/s16/s24/s32, unsigned u8-u32, float f32/f64 (le/be), with sample_rate and num_channels. | encoding pcm_s16le, pcm_s32le, pcm_f16le, pcm_f32le, pcm_mulaw, pcm_alaw with explicit sample_rate; ~100 ms binary chunks. |
| Audio out | n/a | n/a | n/a |
| Languages | Multilingual (Whisper). | 60+ languages with language identification and mixed-language robustness; realtime translation across 3,600+ language pairs (vendor). | ink-whisper takes an ISO-639-1 language (default en); ink-2 language coverage not captured. |
| Latency (vendor claim) | Vendor: real-time speed factor 189x (v3) to 216x (turbo) for files; not a streaming latency. | No numeric vendor claim captured; model notes cite 'faster semantic endpointing'. | No numeric claim captured. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Not re-verified. | Not re-verified in this pass. | Enterprise plans list DPAs and BAAs; not re-verified. |
| Self-hostable | No | No | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/hour | $0.04 | $0.12 | $0.39 |
| Bills silence | - | - | Yes |
| Free tier | Yes | - | Yes |
| Free credit $ | - | - | - |
| Live speakers | No | Yes | - |
| Turn detect | No | Yes | Yes |
| Keyterms | - | Yes | Yes |
| PII redact | - | - | - |
| Partials | No | Yes | Yes |
| Mixed langs | - | Yes | - |
| 8 kHz phone | - | - | Yes |
| Latency ms | - | - | - |
| Languages | - | 60 | - |
| Max session min | - | 300 | - |
| Concurrency | - | 10 | 12 |
| WebRTC | No | No | No |
| WebSocket | No | Yes | Yes |
| gRPC | No | No | No |
| HIPAA | - | - | Yes |
| SOC 2 | - | - | - |
| EU data | - | - | - |
| Self-host | No | No | No |
| Open weights | Yes | No | No |
| High warnings | 1 | 1 | 1 |