Compare realtime APIs

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

Gradium TTS
Gradium
Cartesia Sonic
Cartesia
Rime TTS (Coda, Mist v3)
Rime Labs
CategoryText-to-speechText-to-speechText-to-speech
StatusBetaGAGA
Est. per minute$0.032 - 0.052$0.034 - 0.059$0.027 - 0.045
How that was worked out900 chars/min; L plan ~$35.9/1M vs XS ~$57.8/1M900 chars/min at 1 credit/char. Low = Scale plan effective ~$37.4/1M; high = Pro overage $65/1M.900 chars/min; Mist v3 vs Coda at Starter rates
Pricing modelsubscriptionsubscriptionper-character
Free tier45K credits/month, non-commercial20K credits/month, overages blocked; commercial use not listed for Free (Pro and up: yes).Page conflicts: '~800 minutes free (about 800k characters)' vs FAQ '3,000 free minutes'
Connects byWebSocketWebSocket, HTTP chunked, SSEWebSocket, HTTP chunked
Audio inTextText (no SSML required; break tags supported)Text (custom pronunciation via spell() and dictionaries)
Audio outNot verifiedRaw container; pcm_f32le, pcm_s16le, pcm_mulaw, pcm_alaw at 8000/16000/22050/24000/44100/48000 Hz on the WebSocketpcm, mp3, mulaw (audioFormat); sample rates per model reference
LanguagesEnglish, French, German, Spanish, Portuguese (AWS Marketplace listing)44 (Sonic 3.6)Coda: 8; Mist v3: 4
Latency (vendor claim)Vendor: ~200 ms first audio; vendor-reported Coval P50 TTFA 158 ms.Third-party sources quote Cartesia's claims of ~90 ms time-to-first-audio for Sonic 3 and ~40 ms for Sonic Turbo; Sonic 3.6 described as sub-90 ms. Independent benchmarks reported 128-166 ms medians including network for Sonic 3/3.5.Vendor: sub-200 ms end-to-end via cloud API; Mist v3 typical TTFB well below 100 ms; Coda sub-100 ms model latency on GPU engine (self-hosted) plus 25-50 ms network from most of the US.
Key limits
  • TTS concurrency: Free 2, XS/S 5, M 10, L 15
  • TTS concurrency: Free 2, Pro 3, Startup 5, Scale 15
  • max_buffer_delay_ms default 3000 (0-5000)
  • voice and output_format must stay constant within a context
  • Overages must be enabled; Free stops at the credit cap
  • Starter: 20 concurrent TTS generations
  • Rime keeps only one active contextId at a time per socket
High-severity warnings
  • Free tier is non-commercial
  • None
  • Arcana is gone from the cloud
ComplianceNot verified.Not verified in this pass (enterprise custom terms available).Enterprise: BAA and SOC 2 reports; optional request-data retention controls (disabled by default).
Self-hostableNoNoYes
Last checked2026-10-102026-10-102026-10-10
Key numbers and features
$/1M chars$57.8$50$50
Free tierYesYesYes
Free credit $---
Free tier commercialNoNo-
Voices---
Cloning-Yes-
Instant clone-Yes-
Text stream inYesYesYes
Timestamps-YesYes
Emotion-Yes-
SSML---
8 kHz phone-YesYes
Latency ms20090200
Languages5448
Max session min---
Concurrency5320
WebRTCNoNoNo
WebSocketYesYesYes
gRPCNoNoNo
HIPAA--Yes
SOC 2--Yes
EU data---
Self-hostNoNoYes
Open weightsNoNoNo
High warnings101