Soniox Text-to-Speech
Launched April 23, 2026 by the Soniox STT company: streaming TTS in 60+ languages that starts audio as text arrives, priced at about $0.70 per hour of generated speech.
Overview
Best for: Very low-cost multilingual streaming TTS, especially if you already use Soniox STT.
At a glance
Token-billed; vendor equivalent about $0.70 per hour of speech, which is about $13/1M chars at 900 chars/min. 60+ languages. Timestamps are character level. Launched April 2026; protocol details unverified. Generated audio not stored.
Text, streamed
Not verified
60+ (vendor launch post)
Not verified
No numeric claim verified.
Not verified
Vendor says generated audio is not stored and not used for training.
Features
- input streaming
- character-level timestamps (per comparison page)
- no storage of generated audio (vendor)
Pricing
| What | Price | Unit |
|---|---|---|
| Input text tokens | $4.00 | per 1M tokens |
| Output audio tokens | $21.50 | per 1M tokens |
| Approximate | $0.70 | per hour of generated speech |
Vendor ~$0.70/hour = $0.0117/min
Free tier: Not verified
Source: soniox.com
Setup
- Create a Soniox API key.
- Use the official SDKs (Python, Node, Web, React, React Native) or the TTS API reference.
Endpoint
See Soniox TTS docs (third-party code references tts-rt.soniox.com)Authentication
API key
Warnings
Token billing
Cost depends on audio tokens produced, so pacing affects price; the $0.70/hour figure is an approximation.
Young product
Launched April 2026; protocol details were not verifiable in this pass.
Unverified integration details
WebSocket URL, message schema, audio formats, voices and concurrency were not confirmed from official docs here; prototype before committing.
Plus 12 warnings that apply to all text-to-speech, streaming APIs. See category warnings.
Limits
- Not published for TTS
Models and products
| Name | Status |
|---|---|
| Soniox TTS v2 (tts-rt-v2 per third-party code) | GA |
Docs and sources
Docs
Sources used
Endpoints, formats, voices, concurrency.