As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/soniox-tts-v2/

# Soniox TTS v2

Soniox, Soniox TTS family. Status: current. Type: speech and audio. Released: 2026-08-10.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Soniox API (real-time streaming, WebSocket) | `tts-rt-v2` |  | https://soniox.com/text-to-speech |

## Pricing

- Input: $4 per 1M tokens
- Output: $21.50 per 1M tokens
- Unit as published: USD per 1M tokens (text in / audio out); ≈ $0.70 per hour of generated speech (1 hour ≈ 30,000 audio tokens)
- Source: https://soniox.com/pricing
- Last checked: 2026-09-29

## Specs

- Input: text, audio
- Output: audio
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 36. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from Soniox: Soniox v5 (Async and Real-Time STT) (2026-06-11) https://postcutoff.com/m/soniox-stt-v5/
- Closed weights; access is hosted only.

## What stands out

- 60+ languages in one model, mid-sentence switching: Single multilingual model with mixed-language text and mid-sentence language switching; Soniox claims 'hallucination-free' output (no invented or dropped words) and accurate reading of emails, phone numbers and IDs. Source: https://soniox.com/blog/soniox-text-to-speech
- Audio tags and 20-second voice cloning (v2): TTS v2 adds expressive audio tags (whispering, laughter, hesitation, excitement), voice cloning from ~20 s of reference audio, and character-level timestamps. Source: https://audioxpress.com/news/soniox-tts-v2-adds-expressive-control-and-voice-cloning-to-its-multilingual-voice-ai-platform

## Notes

Soniox launched TTS on 2026-04-23 (tts-rt-v1); TTS v2 (tts-rt-v2, replacing v1) was reported by audioXpress on 2026-08-10. Streaming only; regions US, EU, Japan. The v2 date is from secondary press, not a Soniox post.

Soniox's text-to-speech, the companion to its [v5 STT](soniox-stt-v5.md), aimed at multilingual voice agents.

Sources: https://soniox.com/blog/soniox-text-to-speech , https://soniox.com/pricing , https://audioxpress.com/news/soniox-tts-v2-adds-expressive-control-and-voice-cloning-to-its-multilingual-voice-ai-platform

Model page: https://postcutoff.com/m/soniox-tts-v2/