Soniox TTS v2
Speech and audio
tts-rt-v2
$4 in, $21.50 out per 1M tokens
Soniox v5 (Async and Real-Time STT)
Soniox’s speech-to-text generation for 2026: a single multilingual model family for files (async) and streaming (real-time).
Model idstt-async-v5
Price$1.50 in, $3.50 out per 1M tokens
Checked29 September 2026
Where it stands
51newer speech and audio models since its release
- NVIDIA Nemotron 3.5 Transcribe (30B-A4B)28 Oct 2026
- Hy-SimulMT-30B-A3B22 Oct 2026
- Eleven Realtime v1 Max / Mini20 Oct 2026
- Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)20 Oct 2026
- Voxtral Small Transcribe 320 Oct 2026
The 5 newest are listed. All speech and audio models
- After it from Soniox
- Soniox TTS v210 Aug 2026
- Weights
- Closed weights; access is hosted only.
How to call it
3 ways to use Soniox v5 (Async and Real-Time STT), with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Soniox API (async / file) | stt-async-v5 |
soniox.com | |
| Soniox API (real-time streaming) | stt-rt-v5 |
soniox.com | |
| Web app | soniox.com |
Pricing
| Input | $1.50 per 1M tokens |
|---|---|
| Output | $3.50 per 1M tokens |
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: soniox.com, checked 29 September 2026.
Specs
- Input
- Audio and text
- Output
- Text
- Context window
- Not published
- Max output
- Not published
- Open weights
- No
- Licence
- Proprietary
- Released
- 11 June 2026
- Status
- Current
- Type
- Speech and audio
What stands out
What its maker marketed at launch, and what people found later, each with its source.
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).
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.
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.
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