Soniox

@soniox_ai

Low-latency real-time speech-to-text, text-to-speech and translation APIs.

United States

soniox.com

Replies Reposts Media Articles

Pinned
Soniox
@soniox_ai
Aug 11
Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency
00:00
85
Soniox
@soniox_ai
Sep 7
Soniox STT has native semantic endpointing built directly into real-time transcription across all 60+ supported languages. Most speech-to-text systems still rely on silence-based VAD to determine when someone has stopped speaking. Google and ElevenLabs, for example, expose
7
Soniox
@soniox_ai
Sep 4
We’ve shipped a major improvement to voice cloning in Soniox TTS v2. You can now create an instant voice clone from up to 2 minutes of reference audio, compared with 20 seconds before. The longer sample gives the model much more information about the voice, including phonemes,
00:00
3
Soniox
@soniox_ai
Sep 2
Meta says its new Muse Voice Transcribe leads streaming speech-to-text benchmarks. Muse Voice Transcribe is now live in Soniox Compare STT. Run Meta and Soniox side by side on the same audio and judge for yourself. What we’re seeing: • Meta trained Muse on 70+ languages, but
00:00
1
Soniox
@soniox_ai
Aug 31
Soniox is now live in India with full data residency and lower latency. Customers can run Soniox STT and TTS entirely within India, with native-speaker accuracy for 10 major Indian languages and seamless mid-sentence language switching, including Hinglish. Initial access is
00:00
5