Reson8 Turns

reson8/turns

Turn-aware streaming endpoint from Reson8 for voice agents, emitting turn-start, turn-end-candidate and turn-end events with adjustable eager and final probability thresholds instead of a continuous transcript stream.

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: "reson8/turns",
  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: $0.0051 / minute
Output Price: —
Input: Audio
Output: Text

Capabilities

Explore what Reson8 Turns supports, then use the API section for a request tailored to this model.

StreamWord timestampsSegment timestampsPricing estimated

Languages

DutchEnglishFrenchGermanItalianPolishPortugueseSpanishSwedish

Model Information

Provider: Reson8
Product: Speech-to-Text
Data Policy: No training
Region: EU (Netherlands)
Input: Audio
Output: Text

Provider Documentation

Playground

Try Reson8 Turns by Reson8. Requests use the selected workspace’s credits and API pricing.

Reson8 Turns

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 Reson8 Turns.

Provider	Context	Output	Input Price	Output Price	Endpoint
Reson8	Not specified	Text	$0.0051 / minute	—	`reson8/turns:reson8`

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

reson8/prerecorded handles uploaded files. reson8/realtime streams interim/final transcripts, supports explicit flush, diarization, custom models, confidence, and word timing. reson8/turns is the separate low-latency turn detector: AudioLab emits turn-end candidates as interim text and emits a final transcript only after turn_end (or after the bounded end-of-audio drain). patterns are structured token patterns, not acoustic keyterm boosting. Reson8 does not publish a public usage rate, so all three catalog prices are marked as estimated.

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: "reson8/turns",
  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`	`reson8/turns` — Required model identifier.
`encoding / sample_rate / channels`	View Accepted Values
`custom_model_id`	View Accepted Values
`include_timestamps / include_words / include_language / include_confidence`	View Accepted Values
`include_interim (realtime)`	View Accepted Values
`diarize / max_speakers`	View Accepted Values
`patterns`	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
Reson8 PrerecordedReson8	Not specified	€0.0034 / minute	—
Reson8 RealtimeReson8	Not specified	$0.0051 / minute	—
MAI-Transcribe 2Microsoft Azure	Not specified	$0.0014 / minute	—
Gemini 3.5 TranscribeGoogle Gemini	Not specified	$0.0043 / minute	—
Saaras v4Sarvam AI	Not specified	₹0.425 / minute	—
saaras-v4-batchSarvam AI	Not specified	₹0.425 / minute	—

View All Speech-to-Text