Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| MiniMax Speech (international) MiniMax | Cartesia Sonic Cartesia | Gradium TTS Gradium | |
|---|---|---|---|
| Category | Text-to-speech | Text-to-speech | Text-to-speech |
| Status | GA | GA | Beta |
| Est. per minute | $0.054 - 0.09 | $0.034 - 0.059 | $0.032 - 0.052 |
| How that was worked out | 900 chars/min; turbo $60/M vs hd $100/M pay-as-you-go | 900 chars/min at 1 credit/char. Low = Scale plan effective ~$37.4/1M; high = Pro overage $65/1M. | 900 chars/min; L plan ~$35.9/1M vs XS ~$57.8/1M |
| Pricing model | per-character | subscription | subscription |
| Free tier | Not verified | 20K credits/month, overages blocked; commercial use not listed for Free (Pro and up: yes). | 45K credits/month, non-commercial |
| Connects by | WebSocket, HTTP chunked | WebSocket, HTTP chunked, SSE | WebSocket |
| Audio in | Text with pause markers <#x#> | Text (no SSML required; break tags supported) | Text |
| Audio out | mp3 (default), pcm, flac, wav, pcmu_raw, pcmu_wav, opus; 8000-44100 Hz (default 32000); mono or stereo | Raw container; pcm_f32le, pcm_s16le, pcm_mulaw, pcm_alaw at 8000/16000/22050/24000/44100/48000 Hz on the WebSocket | Not verified |
| Languages | 40 language_boost values plus auto | 44 (Sonic 3.6) | English, French, German, Spanish, Portuguese (AWS Marketplace listing) |
| Latency (vendor claim) | No millisecond figure on the bidi docs. | 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: ~200 ms first audio; vendor-reported Coval P50 TTFA 158 ms. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Not verified. | Not verified in this pass (enterprise custom terms available). | Not verified. |
| Self-hostable | No | No | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/1M chars | $60 | $50 | $57.8 |
| Free tier | - | Yes | Yes |
| Free credit $ | - | - | - |
| Free tier commercial | - | No | No |
| Voices | - | - | - |
| Cloning | Yes | Yes | - |
| Instant clone | Yes | Yes | - |
| Text stream in | Yes | Yes | Yes |
| Timestamps | - | Yes | - |
| Emotion | Yes | Yes | - |
| SSML | - | - | - |
| 8 kHz phone | Yes | Yes | - |
| Latency ms | - | 90 | 200 |
| Languages | 40 | 44 | 5 |
| Max session min | - | - | - |
| Concurrency | - | 3 | 5 |
| WebRTC | No | No | No |
| WebSocket | Yes | Yes | Yes |
| gRPC | No | No | No |
| HIPAA | - | - | - |
| SOC 2 | - | - | - |
| EU data | - | - | - |
| Self-host | No | No | No |
| Open weights | No | No | No |
| High warnings | 1 | 0 | 1 |