Compare realtime APIs

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

Fireworks AI streaming ASR (deprecated)
Fireworks AI
Groq Whisper (no streaming)
Groq
Soniox Real-time STT (stt-rt-v5)
Soniox
CategorySpeech-to-textSpeech-to-textSpeech-to-text
StatusDeprecatedGAGA
Est. per minute$0$0.00067 - 0.0019$0.002 - 0.0025
How that was worked outDo not plan on this service.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.
Pricing modelper-minuteper-hourper-token
Free tiern/aGroq free tier with rate limits (not detailed here).Not stated on the pricing page.
Connects byWebSocketHTTPS (OpenAI-compatible, file upload)WebSocket
Audio inn/a (deprecated)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.
Audio outn/an/an/a
Languagesn/aMultilingual (Whisper).60+ languages with language identification and mixed-language robustness; realtime translation across 3,600+ language pairs (vendor).
Latency (vendor claim)n/aVendor: 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'.
Key limits
  • Service deprecated.
  • No streaming endpoint.
  • 10-second minimum billed length per request.
  • Free tier file size 25 MB.
  • 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.
High-severity warnings
  • Audio inference deprecated
  • Not a streaming API
  • Default concurrency is only 10
Compliancen/aNot re-verified.Not re-verified in this pass.
Self-hostableNoNoNo
Last checked2026-10-102026-10-102026-10-10
Key numbers and features
$/hour-$0.04$0.12
Bills silence---
Free tier-Yes-
Free credit $---
Live speakers-NoYes
Turn detect-NoYes
Keyterms--Yes
PII redact---
Partials-NoYes
Mixed langs--Yes
8 kHz phone---
Latency ms---
Languages--60
Max session min--300
Concurrency--10
WebRTCNoNoNo
WebSocketYesNoYes
gRPCNoNoNo
HIPAA---
SOC 2---
EU data---
Self-hostNoNoNo
Open weightsNoYesNo
High warnings111