Orca Streaming Text-to-Speech Engine

Orca is an on-device streaming Text-to-Speech engine. Orca is:

• Private; All voice processing runs locally.
• Compact and Computationally-Efficient
• Optimized for LLMs, enabling low-latency voice assistants.
• Cross-Platform:
  • Linux (x86_64)
  • macOS (x86_64, arm64)
  • Windows (x86_64, arm64)
  • Android
  • iOS
  • Web
  • Raspberry Pi (3, 4, 5)

Get Started

Anyone who is using Picovoice needs to have a valid AccessKey. AccessKey is your authentication and authorization token for using Picovoice. It also verifies that your usage is within the limits of your account. You must keep your AccessKey secret!

Sign up for Picovoice Console

Sign up for Picovoice Console. It is free, no credit card required.

Retrieve AccessKey

Log in to your account to get your AccessKey.

Download SDK

Picovoice SDKs are available both on GitHub and via SDK-specific package managers. Follow one of the quick starts to synthesize audio offline using Orca with your newly-created AccessKey.

Voices

Orca Streaming Text-to-Speech can synthesize speech with various voices, each of which is characterized by a model file. Currently, Orca Streaming Text-to-Speech offers default 'female' and 'male' voice models. The model files can be downloaded from the Orca GitHub repository. To synthesize speech with a specific voice, provide the associated model file as an argument to the orca init functions.

Custom Voices

For custom voices in any language, Enterprise Plan customers can engage with Picovoice Consulting.

Speech control

Orca Streaming Text-to-Speech provides a set of parameters to control the synthesized speech. While the default speech rate is 1, values between 0.7 and 1.3 can be used to generate faster or slower speech.

Custom Pronunciation

Orca Streaming Text-to-Speech supports custom pronunciation which can be expressed in ARPAbet format for English and different subsets of IPA for our other languages.

English

French

German

Italian

Japanese

Korean

Portuguese

Spanish

Emotional Control

Custom Orca Streaming Text-to-Speech models generate voices with emotions and styles, including joy, anger, whispering, and shouting. Enterprise Plan customers can engage with Picovoice Consulting for emotional control.