Trusted by
1{
2 "text": "<speak>Hello there, <prosody rate=\"40%\">how are</prosody> you today?</speak>",
3 "voicelab_recipe": {
4 "performer": {
5 "voice": "2bfc6875-308c-4101-bf4d-7c279bc56db2",
6 "style": "07e62901-72c4-46e5-b009-aa0938d749df"
7 },
8 "model_chain": "vox_1_0",
9 "voice_config": {
10 "918e6a69-90d7-436d-8301-70a5a5a65156": 0.7,
11 "792fc8b4-dcf6-42b6-bb2c-080234f201e3": 0.3
12 },
13 "options": {
14 "auto_pitch": true,
15 "pitch": 0,
16 "rate": 0.5
17 }
18 },
19 "hq": true,
20 "normalize": false
21}
1import requests
2
3url = "https://api.replicastudios.com/speech"
4
5querystring = {"txt":"<speak>Halt! Stop right there!</speak>","speaker_id":"55a0aad5-a739-402f-9cec-36b01ff81a41","extension":"wav","ai_pace":"1","model_chain":"vox_1_0"}
6
7payload = ""
8headers = {"Authorization": "Bearer <SNIP>"}
9
10response = requests.request("GET", url, data=payload, headers=headers, params=querystring)
Use Cases
Synthesize natural sounding voice over and dialogue in multiple languages for a wide range of creative and professional use cases - from video games to podcasts to films.
Voice Lab
Describe your voice, or the role or character you would like the AI to portray, and dream it into existence with Voice Lab, a prompt-to-voice design feature which can create a blend of up to 5 Replica voices which all contribute their unique accents, prosody, and other vocal features to the resulting new voice.
Save voices into your library for use in video games, audiobooks, social media, educational or corporate videos and real time conversational solutions.
Voice Director
With Replica Voice Director, generate voice overs and dialogue instantly with text to speech, while also managing the scripts for your project where it’s all tracked in one place.
Whether you're doing early prototyping, in pre-production, or producing final voice overs for your content or projects, Replica’s text to speech will supercharge your creative workflows.
How we ensure Responsible Voice AI
Replica partners with happy and passionate voice actors and trains exclusively on licensed data to create highly versatile, diverse and performant AI voices.
By choosing Replica you are assured full commercial usage rights of voice overs and dialogue generated, with the additional knowledge that our voice actors benefit from any revenue we make.
Enterprise Ready
We partner with professional creators and help unlock the possibilities offered by Responsible Generative AI Voice.
Get started today
Accelerate your content creation and experimentation with Replica’s realistic text-to-speech.
Frequently Asked Questions
Our subscription costs start from $10 per month, and we offer introductory discounts for new users from time to time. You can view all our pricing plans here.
Simply sign up for a Replica Studios account and when asked what plan you would like, select the ‘skip and try for free’ option. Multi-language is currently only available in the web based application.
Yes! At Replica, we prioritize Responsible voice ai by collaborating with enthusiastic and consenting voice actors. Our training process exclusively utilizes open source and licensed data, resulting in the development of incredibly versatile, diverse, and high-performance AI voices.
Replica has signed a ground breaking agreement with The Screen Actors Guild - American Federation of Television and Radio Artists (SAG-AFTRA). See more
“Replica is proud to partner with SAG-AFTRA to introduce an ethical approach to the emerging use of generative AI. We are excited by the new opportunities this opens up for world-leading AAA studios who can now access the benefits of Replica’s AI voice technology while knowing that talent is recognized and compensated fairly for the use of their likeness,” - Shreyas Nivas, CEO of Replica Studios.
Multilingual TTS refers to the capability of a system to convert written text into spoken language in multiple languages. It's a technology that's increasingly important in our interconnected world, where communication across language barriers is common.
The goal of multilingual TTS is to produce natural and intelligible speech in various languages, allowing users to interact with devices, applications, and services regardless of their native language.
Multilingual TTS systems often support a wide range of languages and dialects, covering major languages spoken around the world. These systems are used in various applications such as film, animation and audiobook production, language learning platforms, accessibility tools for the visually impaired and navigation systems etc.
Game Development
Multilingual TTS enriches gaming experiences by providing dynamic voiceovers for characters, instructions, and narrative elements in multiple languages. It enhances immersion for players in international markets, allowing them to engage with the game in their native language without the need for extensive localization efforts.
Education and Learning
In educational contexts, multilingual TTS facilitates language learning by pronouncing words, phrases, and sentences in different languages. It enables learners to practice pronunciation, comprehension, and fluency across diverse linguistic landscapes, catering to students with varying proficiency levels and learning preferences.
Animation
Multilingual TTS is utilized in animation to generate voice overs for characters, narration, and dialogue in different languages. It streamlines the localization process for animated content, enabling creators to reach global audiences with dubbed or subtitled versions that maintain linguistic authenticity and cultural relevance.
Film
In the film industry, multilingual TTS assists with voice dubbing, subtitling, and accessibility features for international audiences. It ensures that films can be enjoyed by viewers worldwide, regardless of language barriers, by providing accurate and natural-sounding translations of dialogue and narration.
Audiobook Production
Multilingual TTS enhances the accessibility and availability of audiobooks by enabling text-based content to be converted into spoken language in multiple languages. It broadens the audience reach of audiobook publishers, allowing them to cater to diverse linguistic demographics and expand into global markets with minimal production overhead.
Social Media Content Creation
In social media content creation, multilingual TTS empowers creators to generate voiceovers, captions, and subtitles in various languages for videos, podcasts, and multimedia content. It enables them to engage with international audiences, increase content accessibility, and drive engagement across different linguistic communities on platforms like YouTube, TikTok, and Instagram.