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-stt-v5/

# Soniox v5 (Async and Real-Time STT)

Soniox, Soniox STT family. Status: current. Type: speech and audio. Released: 2026-06-11.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Soniox API (async / file) | `stt-async-v5` |  | https://soniox.com/docs/stt/models |
| Soniox API (real-time streaming) | `stt-rt-v5` |  | https://soniox.com/docs/stt/models |
| Web app |  |  | https://soniox.com |

## Pricing

- Input: $1.50 per 1M tokens
- Output: $3.50 per 1M tokens
- Unit as published: USD per 1M tokens for async (audio in $1.50, text in/out $3.50; ~$0.10 per audio hour). Real-time: $2.00 audio in, $4.00 text in/out (~$0.12/hour). 1 hour of audio ≈ 30,000 input tokens.
- Source: https://soniox.com/pricing
- Last checked: 2026-09-29

## Specs

- Input: audio, text
- Output: text
- 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: 51. 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/
- After it from Soniox: Soniox TTS v2 (2026-08-10) https://postcutoff.com/m/soniox-tts-v2/
- Closed weights; access is hosted only.

## What stands out

- One multilingual model for 60+ languages with speaker separation: Soniox claims native-speaker accuracy across 60+ languages in a single model, re-engineered speaker diarization, spoken-language ID, context injection and precise alphanumerics (IDs, emails, codes). Source: https://soniox.com/blog/soniox-v5-async
- Real-time translation and semantic endpointing: stt-rt-v5 transcribes and translates live across ~3,600 language pairs, with a tunable `endpoint_sensitivity` semantic endpointing parameter for voice agents. Source: https://soniox.com/blog/soniox-v5-real-time

## Notes

stt-async-v5 released 2026-06-11, stt-rt-v5 on 2026-06-16. The v4 ids (stt-async-v4 from 2026-01-29, stt-rt-v4 from 2026-02-05) were retired 2026-06-30 and are now aliases routing to v5. Launch posts give no WER numbers; Soniox publishes its own comparisons at soniox.com/benchmarks (vendor-run). Sibling TTS: soniox-tts-v2.

Soniox's speech-to-text generation for 2026: a single multilingual model family for files (async) and streaming (real-time).

Sources: https://soniox.com/blog/soniox-v5-async , https://soniox.com/blog/soniox-v5-real-time , https://soniox.com/docs/stt/models , https://x.com/soniox_ai/status/2065083564027257182

Model page: https://postcutoff.com/m/soniox-stt-v5/