Soniox (@soniox

Soniox

393 posts

Soniox

@soniox_ai

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

United States

Joined March 2022

Pinned
Soniox
@soniox_ai
Jun 16
Soniox v5 Real-Time is now available. Live speech AI is not batch transcription with lower latency. It has to turn raw, noisy, continuous audio into structured intelligence while people speak. What’s new: • Higher accuracy across 60+ languages • Completely reengineered
Soniox
@soniox_ai
Jul 10
World-leading AI is not enough. To power production applications globally, the infrastructure behind the AI must be just as formidable. 🧵 Soniox is fully deployed across three major global regions: 🇺🇸 United States 🇪🇺 European Union 🇯🇵 Japan
Soniox
@soniox_ai
Jul 10
Replying to @soniox_ai
Behind every API request is a global production system engineered for high availability, automated scaling, fault isolation, observability, and reliable real-time processing at scale.
Soniox
@soniox_ai
Jul 10
We have invested enormous engineering effort into making Soniox more than world-leading voice AI. It is global infrastructure companies can trust for their most critical applications. Build locally. Deploy globally. Serve the world.
Data residency
From soniox.com
Soniox
@soniox_ai
Jul 9
Soniox STT is smart out of the box. Medical terms, legal jargon, technical vocabulary, it knows all of that. But when a pilot calls out "TOGA," a model without context hears a toga. Your internal product names don't stand a chance either. 🧵
Soniox
@soniox_ai
Jul 9
Replying to @soniox_ai
Restaurant taking phone orders? Set "restaurant: Spice India, location: London, setting: phone ordering" in general, add your menu in terms. The model already knows what paneer tikka is. What it can't know is the signature dish name you invented last month, and now it will hear
Soniox
@soniox_ai
Jul 9
Drug names, SKUs, invented words. Skip common vocabulary, the model has that covered. All of it fits in about 10,000 characters. Enough to onboard the model into your world. Learn more:
soniox.com
Context
Learn how to use custom context to enhance trancription accuracy.
Soniox
@soniox_ai
Jul 8
Streaming TTS becomes much more powerful when you know exactly when each part of the text was spoken. Soniox Text-to-Speech now supports character-level timestamps alongside streaming audio. For each character in the generated text, Soniox returns the start and end time of the
00:00
Soniox
@soniox_ai
Jul 7
Soniox Endpoint Detection delivers.
realmatt
@lkcv_7299
Jul 7
@soniox_ai are the goats for Spanish STT 😍 looking good, first impressions
Soniox
@soniox_ai
Jul 7
Soniox Text-to-Speech now supports: • Speed control • Character-level timestamps Speed control is learned at the model level, not applied as audio post-processing, so speech stays natural. Timestamps let you sync generated audio with text in real time, useful for live
Soniox
@soniox_ai
Jul 7
Advice on voice cloning Soniox TTS can clone a voice from a short (up to 20 seconds) sample. The clone works reliably in all 60+ supported languages, but only if the recording is good. How to make a good recording: 🧵
Soniox
@soniox_ai
Jul 7
Replying to @soniox_ai
Read something plain and declarative. No questions, no exclamations. Hesitations and restarts get cloned too. About 60 words fills 20 seconds at a normal pace.
Soniox
@soniox_ai
Jul 7
Upload the sample through Soniox API or in the Soniox Console, get the voice ID, and use it like any other voice in the API. Docs:
Voice cloning
From soniox.com
Soniox
@soniox_ai
Jul 7
Replying to @soniox_ai
Speak in a steady tone for up to 20 seconds. Large swings in volume or pitch make the clone unstable. The tone you record is the tone the clone speaks in, in every language.
Soniox
@soniox_ai
Jul 6
Can you tell which voice is real? Is it sample A or B? Generating a voice that sounds good for one sentence is easy. The hard part is preserving the speaker's tone, rhythm, accent, pronunciation, delivery, and personality across real use cases: voice agents, narration, ads,
00:00
Soniox
@soniox_ai
Jul 2
Don't forget: Soniox Voice Cloning is available also through Soniox API soniox.com/docs/api-refer… 🚀
Create voice
From soniox.com