Unreal Speech Reviews:text to speech AI APIs

Free AI api1年前 (2023)更新 Prompt engineer

10,447 0 90

Table of Contents

About Unreal Speech

Unreal Speech is a text-to-speech API that offers natural-sounding voices, low latency, high uptime, and pricing that scales as your usage grows. You can start with 1 million free characters per month, then take advantage of volume discounts at higher tiers. Unreal Speech has an easy to integrate API with client libraries for many languages. There’s also a live demo on their website which lets you freely test out their TTS with 4 different voices.

Unreal Speech Reviews:text to speech AI APIs

Slash Text-to-Speech Costs by up to 95%

Up to 20x cheaper than Eleven Labs and Play.ht.
Up to 4x cheaper than Amazon, Microsoft, and Google.

Unreal Speech saved us 75% on our text-to-speech cost. It sounds better than Amazon Polly, and is much cheaper. We switched over at high volumes, and often processing 10,000+ pages per hour. Unreal was able to handle the volume, while delivering a high quality listening experience.

Unreal Speech Studio

Make studio-quality voice overs for podcasts, videos & more.

Code Samples

Get started quickly with our simple text-to-speech API.

short

# Short endpoint: /stream
# - Up to 500 characters
# - Synchronous, instant response (0.3s+)
# - Streams back raw audio data

import requests

response = requests.post(
  'https://api.v6.unrealspeech.com/stream',
  headers = {
    'Authorization' : 'Bearer YOUR_API_KEY'
  },
  json = {
    'Text': '''<YOUR_TEXT>''', # Up to 500 characters
    'VoiceId': '<VOICE_ID>', # Dan, Will, Scarlett, Liv, Amy
    'Bitrate': '128k', # 320k, 256k, 192k, ...
    'Speed': '0', # -1.0 to 1.0
    'Pitch': '1', # -0.5 to 1.5
    'Codec': 'libmp3lame', # libmp3lame or pcm_mulaw
  }
)

with open('audio.mp3', 'wb') as f:
    f.write(response.content)

long

# Long endpoint: /synthesisTasks
# - Up to 500,000 characters
# - Asynchronous, takes ~1s per 800 chars
# - Returns a TaskId (use to check status)

import requests

response = requests.post(
  'https://api.v6.unrealspeech.com/synthesisTasks',
  headers = {
    'Authorization' : 'Bearer YOUR_API_KEY'
  },
  json = {
    'Text': '''<YOUR_TEXT>''', # Up to 500,000 characters
    'VoiceId': '<VOICE_ID>', # Dan, Will, Scarlett, Liv, Amy
    'Bitrate': '128k', # 320k, 256k, 192k, ...
    'Speed': '0', # -1.0 to 1.0
    'Pitch': '1', # -0.5 to 1.5
    'TimestampType': 'sentence', # word or sentence
   #'CallbackUrl': '<URL>', # pinged when ready
  }
)

print(response.json())
Sample Response
{
  'SynthesisTask': {
    'CreationTime': '2023-09-01T15:05:22.15Z',
    'OutputUri': 'https://unreal-tts-live-demo.s3-us-west-1.amazonaws.com/d8ef514d.mp3',
    'RequestCharacters': 14,
    'TaskId': 'd8ef514d',
    'TaskStatus': 'scheduled',
    'TimestampsUri': 'https://unreal-tts-live-demo.s3-us-west-1.amazonaws.com/d8ef514d.json',
    'VoiceId': 'Scarlett'
  }
}
Check Task Status
Make a GET request with TaskId in the URL to check the status.
import requests

response = requests.get(
  'https://api.v6.unrealspeech.com/synthesisTasks/d8ef514d',
  headers = {
    'Authorization' : 'Bearer YOUR_API_KEY'
  },
  json = {}
)

print(response.json())