GA Unreal Speech

Unreal Speech

Budget TTS with a /stream endpoint that returns audio in about 0.3 s for up to 1,000 characters. No WebSocket input streaming.

Est. per minute$0.0072 - 0.015

Overview

Best for: Cheap English narration and simple bots that can tolerate per-sentence HTTP requests.

At a glance

$/1M chars$16.33
Free tierYes
Text stream inNo
TimestampsYes
Latency ms300
Languages6
WebRTCNo
WebSocketNo
gRPCNo
Self-hostNo
Open weightsNo

Price is the Basic plan list rate ($49 for 3M chars); promo $4.99/month for the first 6 months; Enterprise about $8/1M. /stream returns audio in ~0.3 s (vendor), 1,000 chars per request. Word timestamps on /speech only. Free 250K chars/month.

Audio in

Text

Audio out

MP3 (bitrate 16k-320k, default 192k); other formats not verified

Languages

English plus Chinese, Spanish, French, Hindi, Italian voices (V8 voice list)

Voices

Catalog voices by language/gender; no cloning documented

Latency

Vendor: /stream returns audio in ~0.3 s.

Regions

Not specified

Compliance

Not verified.

Features

  • streaming HTTP output
  • word timestamps on /speech
  • async long-form up to 500K chars

Pricing

WhatPriceUnitNotes
Free$0monthly250K characters (~6 h)
Basic$49/month ($4.99 first 6 months)monthly3M characters
Plus$499/monthmonthly42M characters
Pro$1,499/monthmonthly150M characters
Enterprise$4,999/monthmonthly625M characters
How the per-minute estimate was worked out

900 chars/min at plan-included rates: Enterprise $8/1M to Basic $16.3/1M (list price). Vendor itself assumes 750 chars/min.

Free tier: 250K characters/month

Source: unrealspeech.com

Setup

  1. Get an API key from unrealspeech.com.
  2. POST JSON {Text, VoiceId, Bitrate} to https://api.v8.unrealspeech.com/stream.
  3. Write the returned audio bytes as they arrive.

Endpoint

https://api.v8.unrealspeech.com/stream

Authentication

Authorization: Bearer <UNREAL_SPEECH_API_KEY>

Quick start python

# pip install requests
import os, requests

r = requests.post(
    "https://api.v8.unrealspeech.com/stream",
    headers={"Authorization": f"Bearer {os.environ['UNREAL_SPEECH_API_KEY']}"},
    json={"Text": "Hello from Unreal Speech.", "VoiceId": "Hannah", "Bitrate": "192k"},
    stream=True, timeout=30)
r.raise_for_status()
with open("out.mp3", "wb") as f:
    for chunk in r.iter_content(4096):
        f.write(chunk)

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

1,000-character cap on /stream

Long LLM replies need splitting into several /stream calls.

Promotional first-month pricing

Basic shows $4.99/month for the first 6 months, then $49/month.

Host version confusion

Docs reference both api.v7 and api.v8 hosts; voice lists differ between versions. Use the host matching your docs version.

No overage price published

The pricing page does not list per-1M overage rates or concurrency limits.

Plus 12 warnings that apply to all text-to-speech, streaming APIs. See category warnings.

Limits

  • /stream 1,000 chars per request
  • /speech 3,000 chars
  • /synthesisTasks 500,000 chars

Models and products

NameStatusNotes
API v8 (/stream, /speech, /synthesisTasks)GASome specs still reference api.v7 host.

Docs and sources

Docs

Sources used

Not fully verified

Auth header format, voice names on v8, output formats other than MP3, concurrency.

Similar text-to-speech APIs

Spotted a wrong price or a dead link?