Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| xAI Grok TTS xAI | SpeechifyAI (Simba 3.2 / 3.0) Speechify | Inworld TTS (Realtime TTS-2, TTS-2 Flash) Inworld AI | |
|---|---|---|---|
| Category | Text-to-speech | Text-to-speech | Text-to-speech |
| Status | Beta | GA | GA |
| Est. per minute | $0.0038 - 0.013 | $0.0054 - 0.009 | $0.0063 - 0.022 |
| How that was worked out | 900 chars/min at $4.20/1M (beta) vs $15/1M; unverified which applies | 900 chars/min at $6 (Scale) to $10 (Starter) per 1M | 900 chars/min. Low = TTS-2 Flash on Growth ($7/1M); high = TTS-2 on On-Demand ($25/1M). |
| Pricing model | per-character | per-character | per-character |
| Free tier | Not verified | 500K characters/month; commercial use on every plan (vendor) | On-Demand: up to 70 minutes of TTS |
| Connects by | WebSocket, HTTP chunked | HTTP chunked | WebSocket, HTTP chunked |
| Audio in | Text | Text and SSML (pauses, speaking rate) | Text with inline tags (pauses, pronunciation, steering on TTS-2) |
| Audio out | MP3, WAV, PCM, mu-law, A-law | 5 formats including mp3 (per marketing page) | LINEAR16 (WAV header per chunk), PCM, MP3 (default), OGG_OPUS, ALAW, MULAW, WAV; 8-48 kHz (default 48 kHz) |
| Languages | Not verified | English (simba-3.2) plus 5 more on simba-3.0 | Docs say 200+ languages and locales; release notes describe 15 production-quality plus 90+ experimental for TTS-2 |
| Latency (vendor claim) | Vapi measured 285 ms median for the streaming variant (June 2026, includes network). | Vendor: 56 ms p50 first byte; independent: 106 ms (Coval) and 123 ms (Voice Arena) median time to first audio. | Vendor: P90 server-side TTFB 100 ms (TTS-2), 20 ms (TTS-2 Flash). |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Not verified. | Not verified. | Zero data retention supported (models page). Certifications not re-verified. |
| Self-hostable | No | No | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/1M chars | - | $5.26 | $25 |
| Free tier | - | Yes | Yes |
| Free credit $ | - | - | - |
| Free tier commercial | - | Yes | - |
| Voices | - | - | - |
| Cloning | - | Yes | Yes |
| Instant clone | - | - | - |
| Text stream in | Yes | No | Yes |
| Timestamps | - | - | Yes |
| Emotion | - | - | Yes |
| SSML | - | Yes | - |
| 8 kHz phone | Yes | - | Yes |
| Latency ms | - | 56 | 100 |
| Languages | - | 6 | 15 |
| Max session min | - | - | - |
| Concurrency | 10 | - | 5 |
| WebRTC | No | No | No |
| WebSocket | Yes | No | Yes |
| gRPC | No | No | No |
| HIPAA | - | - | - |
| SOC 2 | - | - | - |
| EU data | No | - | - |
| Self-host | No | No | No |
| Open weights | No | No | No |
| High warnings | 1 | 0 | 0 |