@@ -23,9 +23,6 @@ voice assistants. Orca is:
2323 - Raspberry Pi (3, 4, 5)
2424 - Chrome, Safari, Firefox, and Edge
2525
26- ** Please note that Orca is currently in development. While we prioritize stability and compatibility, certain aspects of
27- Orca may undergo changes as we continually enhance and refine the engine to provide the best user experience possible.**
28-
2926## Table of Contents
3027
3128- [ Orca] ( #orca )
@@ -57,15 +54,15 @@ Orca may undergo changes as we continually enhance and refine the engine to prov
5754
5855## Language Support
5956
60- - Orca Text-to-Speech currently supports English only.
57+ - Orca Streaming Text-to-Speech currently supports English only.
6158- Support for [ additional languages is available for commercial customers] ( https://picovoice.ai/consulting/ ) on a
6259 case-by-case basis.
6360
6461## Overview
6562
6663### Orca input and output streaming synthesis
6764
68- Orca is a text-to-speech engine designed specifically for LLMs. It can process
65+ Orca is a streaming text-to-speech engine designed specifically for LLMs. It can process
6966incoming text streams in real-time, generating audio continuously, i.e., as the LLM produces tokens,
7067Orca generates speech in parallel.
7168This enables seamless conversations with voice assistants, eliminating any audio delays.
@@ -76,9 +73,9 @@ Orca also supports single synthesis mode, where a complete text is synthesized i
7673
7774### Text input
7875
79- Orca accepts the 26 lowercase (a-z) and 26 uppercase (A-Z) letters of the English alphabet, numbers,
80- basic symbols, as well as common punctuation marks. You can get a list of all supported characters by calling the
81- ` valid_characters() ` method provided in the Orca SDK you are using.
76+ Orca supports a wide range of English characters, including letters, numbers, symbols, and punctuation marks.
77+ You can get a list of all supported characters by calling the ` valid_characters() ` method provided
78+ in the Orca SDK you are using.
8279Pronunciations of characters or words not supported by this list can be achieved with
8380[ custom pronunciations] ( #custom-pronunciations ) .
8481
@@ -683,6 +680,13 @@ For more details, see the [Node.js SDK](./binding/nodejs/).
683680
684681## Releases
685682
683+ ### v1.0.0 - Aug 20th, 2024
684+
685+ - Improved voice quality
686+ - Significantly reduced latency in streaming synthesis
687+ - Reduced model size
688+ - Advanced text normalization
689+
686690### v0.2.0 - May 3rd, 2024
687691
688692- Support for streaming synthesis
0 commit comments