CHECKED OCT 10, 2026

Compare realtime APIs

Pick up to four APIs from any category and see them side by side.

Soniox Real-time STT (stt-rt-v5)
Soniox
Cartesia Ink (ink-2, ink-whisper)
Cartesia
AssemblyAI Universal-3.6 Pro Realtime and Universal-Streaming
AssemblyAI
CategorySpeech-to-textSpeech-to-textSpeech-to-text
StatusGAGAGA
Est. per minute$0.002 - 0.0025$0.0022 - 0.012$0.0025 - 0.0095
How that was worked out~$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).$0.15/hr Universal-Streaming = $0.0025/min; $0.45/hr U3.6 Pro + $0.12/hr diarization = $0.0095/min. Session time, so idle open sockets cost the same.
Pricing modelper-tokenper-hourper-hour
Free tierNot stated on the pricing page.Free plan: 20K credits/month (about 1h51m of ink-2 per plan table).$50 free credit at signup, no card required.
Connects byWebSocketWebSocketWebSocket
Audio inaudio_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.Mono 16-bit PCM by default with sample_rate set to the source; mulaw also documented historically; AAC (ADTS, encoding=aac) and Opus (encoding=ogg_opus or opus) accepted. Chunks must be 50-1000 ms and must not arrive faster than real time.
Audio outn/an/an/a
Languages60+ 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.Universal-3.6 Pro: 32 languages with code-switching; 3.5 Pro: 19; Universal-Streaming Multilingual: 6; English model: English only.
Latency (vendor claim)No numeric vendor claim captured; model notes cite 'faster semantic endpointing'.No numeric claim captured.Vendor docs rate the Pro models 'Fastest' and Universal-Streaming 'Fast'; no numeric figure on the model page.
Key limits
  • 100 requests per minute, 10 concurrent streams by default (raisable in console).
  • Each stream capped at 300 minutes; this cap cannot be raised.
  • Open-connection limit is a multiple of the concurrent-request limit, including idle sockets.
  • STT concurrent requests: Free 8, Pro 12, Startup 20, Scale 60, Enterprise custom (separate pool from TTS).
  • With overages disabled, requests fail when credits run out.
  • Rate limit is on NEW sessions per minute, not total open sessions: Free 5/min, paid 100+/min, auto-scales +10% when you use 70%+ of it.
  • Max session 3 hours (error 3008); sessions not terminated auto-close after 3 hours and are billed for the full time.
  • Audio chunk must be 50-1000 ms (error 3007); sending faster than real time is rejected (3007).
  • Too many sessions gives close code 1008/3009.
High-severity warnings
  • Default concurrency is only 10
  • Silence is billed
  • Billed for socket open time
  • Forgotten sessions bill for 3 hours
ComplianceNot re-verified in this pass.Enterprise plans list DPAs and BAAs; not re-verified.US and EU data-zone streaming endpoints documented. Vendor markets SOC 2 and HIPAA BAA; not re-verified in this pass.
Self-hostableNoNoYes
Last checked2026-10-102026-10-102026-10-10
Key numbers and features
$/hour$0.12$0.39$0.45
Bills silence-YesYes
Free tier-YesYes
Free credit $--$50
Live speakersYes-Yes
Turn detectYesYesYes
KeytermsYesYesYes
PII redact--Yes
PartialsYesYesYes
Mixed langsYes-Yes
8 kHz phone-Yes-
Latency ms---
Languages60-32
Max session min300-180
Concurrency1012-
WebRTCNoNoNo
WebSocketYesYesYes
gRPCNoNoNo
HIPAA-YesYes
SOC 2--Yes
EU data--Yes
Self-hostNoNoYes
Open weightsNoNoNo
High warnings112