Enhanced (Realtime)

speechmatics/enhanced-realtime

Speechmatics' top-accuracy model for live audio, running the Enhanced tier over its realtime WebSocket API. Speechmatics says its Ursa 2 generation brought realtime latency under one second; speaker diarization and partial transcripts are supported across 55+ languages.

Get API Key Read the Docs

import WebSocket from "ws";
import { readFile } from "node:fs/promises";

// Use mono, 16 kHz, signed 16-bit little-endian PCM.
const audio = await readFile("recording.pcm");
const url = new URL("/v1/audio/transcriptions/stream", process.env.AUDIOLAB_API_URL);
url.protocol = url.protocol === "https:" ? "wss:" : "ws:";
const socket = new WebSocket(url, {
  headers: { Authorization: `Bearer ${process.env.AUDIOLAB_API_KEY}` },
});
socket.on("open", () => socket.send(JSON.stringify({
  type: "session.start", model: "speechmatics/enhanced-realtime",
  encoding: "pcm_s16le", sample_rate: 16000, channels: 1,
})));
socket.on("message", (data) => {
  const event = JSON.parse(data.toString());
  console.log(event);
  if (event.type === "session.started") {
    for (let offset = 0; offset < audio.length; offset += 3200)
      socket.send(audio.subarray(offset, offset + 3200));
    socket.send(JSON.stringify({ type: "session.finish" }));
  }
});

Input Price: $0.0061 / minute
Output Price: —
Input: Audio
Output: Text

Capabilities

Explore what Enhanced (Realtime) supports, then use the API section for a request tailored to this model.

StreamDiarizationWord timestampsSegment timestampsConfidence

Languages

Multilingual

Model Information

Provider: Speechmatics
Product: Speech-to-Text
Release Date: Oct 11, 2024
Data Policy: Configurable
Region: EU
Input: Audio
Output: Text

Provider Documentation

Playground

Try Enhanced (Realtime) by Speechmatics. Requests use the selected workspace’s credits and API pricing.

Enhanced (Realtime)

This model uses a dedicated input format. Explore its API example or open the supported playground.

Open playground

Providers

Compare available endpoints, pricing, and context limits for Enhanced (Realtime).

Provider	Context	Output	Input Price	Output Price	Endpoint
Speechmatics	Not specified	Text	$0.0061 / minute	—	`speechmatics/enhanced-realtime:speechmatics`

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max bytes	Not specified
Max seconds	Not specified
Formats

Provider Notes

Enhanced and Standard are separate batch models; Enhanced Realtime and Standard Realtime are separate streaming products and preserve their own pricing. The current API selects model=enhanced or model=standard; the deprecated operating_point field is not sent. Melia 1 is multilingual transcription with code switching, not the Speechmatics translation feature: it is batch-only, requires language=multi, and rejects custom vocabulary, translation, entity extraction, transcript filtering, and speaker-diarization tuning.

Performance

No measurements in the last 24 hours.

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Checking availability…

A live availability check is not available right now.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

import WebSocket from "ws";
import { readFile } from "node:fs/promises";

// Use mono, 16 kHz, signed 16-bit little-endian PCM.
const audio = await readFile("recording.pcm");
const url = new URL("/v1/audio/transcriptions/stream", process.env.AUDIOLAB_API_URL);
url.protocol = url.protocol === "https:" ? "wss:" : "ws:";
const socket = new WebSocket(url, {
  headers: { Authorization: `Bearer ${process.env.AUDIOLAB_API_KEY}` },
});
socket.on("open", () => socket.send(JSON.stringify({
  type: "session.start", model: "speechmatics/enhanced-realtime",
  encoding: "pcm_s16le", sample_rate: 16000, channels: 1,
})));
socket.on("message", (data) => {
  const event = JSON.parse(data.toString());
  console.log(event);
  if (event.type === "session.started") {
    for (let offset = 0; offset < audio.length; offset += 3200)
      socket.send(audio.subarray(offset, offset + 3200));
    socket.send(JSON.stringify({ type: "session.finish" }));
  }
});

Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

Parameter	Details
`model`	`speechmatics/enhanced-realtime` — Required model identifier.
`additional_vocab / output_locale / domain`	View Accepted Values
`audio_filtering_config / transcript_filtering_config`	View Accepted Values
`diarization / channel_diarization_labels / speaker_diarization_config`	View Accepted Values
`punctuation_overrides / enable_entities`	View Accepted Values
`translation_config`	View Accepted Values
`conversation_config / max_delay / max_delay_mode (realtime)`	View Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max bytes	Not specified
Max seconds	Not specified
Formats

Similar Models

Explore more speech-to-text and compare their capabilities.

Model	Context	Input Price	Output Price
Melia 1Speechmatics	Not specified	$0.0018 / minute	—
EnhancedSpeechmatics	Not specified	$0.0057 / minute	—
StandardSpeechmatics	Not specified	$0.0034 / minute	—
Standard RealtimeSpeechmatics	Not specified	$0.0034 / minute	—
MAI-Transcribe 2Microsoft Azure	Not specified	$0.0014 / minute	—
Gemini 3.5 TranscribeGoogle Gemini	Not specified	$0.0043 / minute	—

View All Speech-to-Text