Soniox: Soniox STT Realtime v5

Name: Soniox STT Realtime v5
Author: Soniox

soniox/stt-rt-v5

active stt 1 provider

Playground

Soniox real-time speech-to-text model for live audio with speaker separation, language identification, translation, and semantic endpointing.

AuthorSoniox

Languagesmultilingual

Statusactive

Quick start

Soniox STT Realtime v5

Create an API key

Create API key

Make a request

Pick an SDK, request mode, and language. The model and provider route are already filled in.

ElevenLabs SDK streaming STT

Streams microphone or file audio through the ElevenLabs-compatible allmodels route.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "soniox/stt-rt-v5",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "soniox"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.

Pass provider parameters

Pass provider preferences through the compatible SDK request options when you want to pin a route to a provider.

{
  queryParams: {
    provider: {
      only: ["soniox"]
    }
  }
}

Providers

Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.

ProviderSlugPer hourLatencyiModesUptime

Soniox 10 params

soniox

From $0.12

—

Streaming

Soniox

10 documented provider parameters for this route.

Pricing

ModeLanguagePer hour

Transcription Only Any $0.12

Input Audio Tokens Any $2 Per 1M tokens

Input Text Tokens Any $4 Per 1M tokens

Output Text Tokens Any $4 Per 1M tokens

With Translation Any $0.18

Parameters

audio_format body · unknown · optional

Mapped from allmodels parameter "audio_format".

context body · unknown · optional

Mapped from allmodels parameter "context".

enable_endpoint_detection body · unknown · optional

Mapped from allmodels parameter "endpoint_detection".

enable_language_identification body · unknown · optional

Mapped from allmodels parameter "language_identification".

enable_speaker_diarization body · unknown · optional

Mapped from allmodels parameter "diarization".

language_hints body · unknown · optional

Mapped from allmodels parameter "language".

model body · unknown · optional

Mapped from allmodels parameter "model".

num_channels body · unknown · optional

Mapped from allmodels parameter "num_channels".

sample_rate body · unknown · optional

Mapped from allmodels parameter "sample_rate".

translation body · unknown · optional

Mapped from allmodels parameter "translation".

Supported languages

No reviewed language list for this model yet.

Features

Speech to text

Transcribes spoken audio to text.

speech_to_text

Streaming

Real-time streaming transcription over WebSocket.

streaming

Multilingual transcription

Supports 60+ languages.

multilingual_transcription

Speaker diarization

Identifies and separates multiple speakers.

speaker_diarization

Word-level timestamps

Returns word-level timestamps.

word_timestamps

Language identification

Automatically identifies the spoken language.

language_identification

Speech translation

Supports real-time / async speech translation.

translation

Semantic endpointing

Provides fast semantic end-of-turn detection.

endpointing

Code

ElevenLabs SDK streaming STT

Streams microphone or file audio through the ElevenLabs-compatible allmodels route.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "soniox/stt-rt-v5",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "soniox"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.