CHECKED OCT 10, 2026

Compare realtime APIs

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

Inworld TTS (Realtime TTS-2, TTS-2 Flash)
Inworld AI
SpeechifyAI (Simba 3.2 / 3.0)
Speechify
Unreal Speech
Unreal Speech
CategoryText-to-speechText-to-speechText-to-speech
StatusGAGAGA
Est. per minute$0.0063 - 0.022$0.0054 - 0.009$0.0072 - 0.015
How that was worked out900 chars/min. Low = TTS-2 Flash on Growth ($7/1M); high = TTS-2 on On-Demand ($25/1M).900 chars/min at $6 (Scale) to $10 (Starter) per 1M900 chars/min at plan-included rates: Enterprise $8/1M to Basic $16.3/1M (list price). Vendor itself assumes 750 chars/min.
Pricing modelper-characterper-charactersubscription
Free tierOn-Demand: up to 70 minutes of TTS500K characters/month; commercial use on every plan (vendor)250K characters/month
Connects byWebSocket, HTTP chunkedHTTP chunkedHTTP chunked
Audio inText with inline tags (pauses, pronunciation, steering on TTS-2)Text and SSML (pauses, speaking rate)Text
Audio outLINEAR16 (WAV header per chunk), PCM, MP3 (default), OGG_OPUS, ALAW, MULAW, WAV; 8-48 kHz (default 48 kHz)5 formats including mp3 (per marketing page)MP3 (bitrate 16k-320k, default 192k); other formats not verified
LanguagesDocs say 200+ languages and locales; release notes describe 15 production-quality plus 90+ experimental for TTS-2English (simba-3.2) plus 5 more on simba-3.0English plus Chinese, Spanish, French, Hindi, Italian voices (V8 voice list)
Latency (vendor claim)Vendor: P90 server-side TTFB 100 ms (TTS-2), 20 ms (TTS-2 Flash).Vendor: 56 ms p50 first byte; independent: 106 ms (Coval) and 123 ms (Voice Arena) median time to first audio.Vendor: /stream returns audio in ~0.3 s.
Key limits
  • Concurrent requests: On-Demand 5, Creator 10, Builder 50, Developer 150, Growth 500
  • 2,000 UTF-16 code units per send_text message
  • Socket closes after 10 min of inactivity across all contexts
  • Sync 2,000 chars, HTTP streaming 4,000 chars, async 100,000 chars per request
  • /v1/audio/stream up to 20,000 characters; /v1/audio/speech up to 2,000
  • Free tier cannot top up
  • /stream 1,000 chars per request
  • /speech 3,000 chars
  • /synthesisTasks 500,000 chars
High-severity warnings
  • None
  • None
  • None
ComplianceZero data retention supported (models page). Certifications not re-verified.Not verified.Not verified.
Self-hostableNoNoNo
Last checked2026-10-102026-10-102026-10-10
Key numbers and features
$/1M chars$25$5.26$16.33
Free tierYesYesYes
Free credit $---
Free tier commercial-Yes-
Voices---
CloningYesYes-
Instant clone---
Text stream inYesNoNo
TimestampsYes-Yes
EmotionYes--
SSML-Yes-
8 kHz phoneYes--
Latency ms10056300
Languages1566
Max session min---
Concurrency5--
WebRTCNoNoNo
WebSocketYesNoNo
gRPCNoNoNo
HIPAA---
SOC 2---
EU data---
Self-hostNoNoNo
Open weightsNoNoNo
High warnings000