SDK Update and Refactor (#76)

## Changes

- Add streaming features
- Add support for pre-recorded features when streaming
- Add Speech to Text
- Refactor Code

### Streaming Features
- endpointing
- utterance_end_ms
- interim_results
- no_delay
- vad_events

### Streaming Functions
- keep_alive

### New Streaming Message Types
- Utterance End
- Speech Started

### Pre-Recorded Features
- encoding
- smart_format
- callback
- callback_method
- filler_words
- paragraphs
- diarize_version
- dictation
- measurements
- extra

### Pre-Recorded Audio Intelligence Features
- detect_entities
- sentiment
- topics
- summarize
- intents
- custom_intents
- custom_intent_mode
- topics
- custom_topics
- custom_topic_mode

Author: DamienDeepgram

.github/workflows/ci.yaml

@@ -5,50 +5,57 @@ env:
   CARGO_TERM_COLOR: always
   RUSTFLAGS: -D warnings
   RUSTDOCFLAGS: -D warnings
+  PKG_CONFIG_PATH: /usr/lib/pkgconfig
 
 jobs:
   Features:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
-    - name: Install libasound2-dev
+    - name: Install dependencies
       run: |
         sudo apt-get update
-        sudo apt-get install libasound2-dev
+        sudo apt-get install -y alsa pkg-config libasound2-dev
+        export PKG_CONFIG_PATH=/usr/lib/pkgconfig:$PKG_CONFIG_PATH
     - name: Check no features
       run: cargo check --all-targets --no-default-features
-    - name: Check prerecorded feature
-      run: cargo check --all-targets --no-default-features --features=prerecorded
-    - name: Check live feature
-      run: cargo check --all-targets --no-default-features --features=live
+    - name: Check listen feature
+      run: cargo check --all-targets --no-default-features --features=listen
+    - name: Check speak feature
+      run: cargo check --all-targets --no-default-features --features=speak
+    - name: Check manage feature
+      run: cargo check --all-targets --no-default-features --features=manage
   Build:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
-    - name: Install libasound2-dev
+    - name: Install dependencies
       run: |
         sudo apt-get update
-        sudo apt-get install libasound2-dev
+        sudo apt-get install -y alsa pkg-config libasound2-dev
+        export PKG_CONFIG_PATH=/usr/lib/pkgconfig:$PKG_CONFIG_PATH
     - name: Cargo Build
       run: cargo build --all-targets --all-features
   Clippy:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
-    - name: Install libasound2-dev
+    - name: Install dependencies
       run: |
         sudo apt-get update
-        sudo apt-get install libasound2-dev
+        sudo apt-get install -y alsa pkg-config libasound2-dev
+        export PKG_CONFIG_PATH=/usr/lib/pkgconfig:$PKG_CONFIG_PATH
     - name: Cargo Clippy
       run: cargo clippy --all-targets --all-features
   Test:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
-    - name: Install libasound2-dev
+    - name: Install dependencies
       run: |
         sudo apt-get update
-        sudo apt-get install libasound2-dev
+        sudo apt-get install -y alsa pkg-config libasound2-dev
+        export PKG_CONFIG_PATH=/usr/lib/pkgconfig:$PKG_CONFIG_PATH
     - name: Cargo Test
       run: cargo test --all --all-features
   Format:
@@ -61,12 +68,19 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
+    - name: Install dependencies
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y alsa pkg-config libasound2-dev
+        export PKG_CONFIG_PATH=/usr/lib/pkgconfig:$PKG_CONFIG_PATH
     - name: Cargo Doc
       run: cargo doc --workspace --all-features
   Audit:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
+    - name: Install dependencies
+      run: sudo apt-get update
     - name: Install cargo-audit
       run: cargo install --locked cargo-audit
     - name: Remove Dev Dependencies
@@ -80,10 +94,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
-    - name: Install libasound2-dev
+    - name: Install dependencies
       run: |
         sudo apt-get update
-        sudo apt-get install libasound2-dev
+        sudo apt-get install -y alsa pkg-config libasound2-dev
+        export PKG_CONFIG_PATH=/usr/lib/pkgconfig:$PKG_CONFIG_PATH
     - name: Install Rust Nightly
       run: rustup toolchain install nightly
     - name: Cargo Build
@@ -101,6 +116,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
+    - name: Install dependencies
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y alsa pkg-config libasound2-dev
+        export PKG_CONFIG_PATH=/usr/lib/pkgconfig:$PKG_CONFIG_PATH
     - name: Install cargo-semver-checks
       run: cargo install --locked cargo-semver-checks
     - name: Cargo SemVer Checks

.gitignore

@@ -1,2 +1,3 @@
 /target
 /Cargo.lock
+your_output_file.wav

CHANGELOG.md

@@ -4,7 +4,89 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [0.6.0] - 2024-07-23
+
+### Migrating from 0.4.0 -> 0.6.0
+
+Module Imports
+
+```
+use deepgram::{
+---    transcription::prerecorded::{
++++    common::{
+        audio_source::AudioSource,
+        options::{Language, Options},
+    },
+    Deepgram, DeepgramError,
+};
+```
+
+Streaming Changes
+
+Now you can pass Options using stream_request_with_options
+```
+let options = Options::builder()
+    .smart_format(true)
+    .language(Language::en_US)
+    .build();
+
+let mut results = dg
+    .transcription()
+    .stream_request_with_options(Some(&options))
+    .file(PATH_TO_FILE, AUDIO_CHUNK_SIZE, Duration::from_millis(16))
+    .await?
+    .start()
+    .await?;
+```
+
+Some Enums have changed and may need to be updated
+
+### Changed
+
+- Add streaming features
+- Add support for pre-recorded features when streaming
+- Add Speech to Text
+- Reorganize Code
+
+### Streaming Features
+- endpointing
+- utterance_end_ms
+- interim_results
+- no_delay
+- vad_events
+
+### Streaming Functions
+- keep_alive
+
+### New Streaming Message Types
+- Utterance End
+- Speech Started
+
+### Pre-Recorded Features
+- encoding
+- smart_format
+- callback
+- callback_method
+- filler_words
+- paragraphs
+- diarize_version
+- dictation
+- measurements
+- extra
+
+### Pre-Recorded Audio Intelligence Features
+- detect_entities
+- sentiment
+- topics
+- summarize
+- intents
+- custom_intents
+- custom_intent_mode
+- topics
+- custom_topics
+- custom_topic_mode
+
+## [0.5.0]
 - Deprecate tiers and add explicit support for all currently available models.
 - Expand language enum to include all currently-supported languages.
 - Add (default on) feature flags for live and prerecorded transcription.

Cargo.toml

@@ -1,65 +1,86 @@
 [package]
 name = "deepgram"
-version = "0.5.0"
+version = "0.6.0"
 authors = ["Deepgram <[email protected]>"]
 edition = "2021"
 description = "Official Rust SDK for Deepgram's automated speech recognition APIs."
 license = "MIT"
 repository = "https://github.com/deepgram-devs/deepgram-rust-sdk"
-keywords = ["deepgram", "asr", "transcription", "ai", "speech-to-text"]
+keywords = ["deepgram", "transcription", "voice ai", "text-to-speech", "tts", "aura", "speech-to-text", "stt", "asr", "nova", "voice agent", "self-hosted"]
 categories = ["api-bindings", "multimedia::audio"]
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
 # TODO Investigate which of these dependencies can go behind features.
+audio = "0.2.0"
 bytes = "1"
 futures = "0.3"
 http = "0.2"
 pin-project = "1"
 reqwest = { version = "0.11.22", default-features = false, features = ["json", "rustls-tls", "stream"] }
-serde = { version = "1", features = ["derive"] }
+rodio = { version = "0.17.0", optional = true }
+serde = { version = "1.0.25", features = ["derive"] }
 serde_json = "1"
+serde_urlencoded = "0.7"
 thiserror = "1"
-tokio = { version = "1.13.0", features = ["full"] }
+tokio = { version = "1.38.0", features = ["full"] }
+tokio-stream = "0.1.15"
 tokio-tungstenite = { version = "0.20.1", features = ["rustls-tls-webpki-roots"], optional = true }
 tokio-util = { version = "0.7.1", features = ["codec", "io"] }
 tungstenite = { version = "0.20.1", optional = true }
 url = "2"
 uuid = { version = "1", features = ["serde"] }
 # Dependencies below are specified only to satisfy minimal-versions.
 proc-macro2 = "1.0.60"
+pkg-config = { version = "0.3.30", optional = true }
 
 [dev-dependencies]
-pkg-config = "0.3.27"
 cpal = "0.13"
 crossbeam = "0.8"
 
 [features]
-default = ["prerecorded", "live"]
-live = ["dep:tungstenite", "dep:tokio-tungstenite"]
-prerecorded = []
+default = ["manage", "listen", "speak"]
+manage = []
+listen = ["dep:tungstenite", "dep:tokio-tungstenite"]
+speak = ["dep:rodio", "dep:pkg-config"]
 
 [[example]]
 name = "prerecorded_from_file"
-required-features = ["prerecorded"]
+path = "examples/transcription/rest/prerecorded_from_file.rs"
+required-features = ["listen"]
 
 [[example]]
 name = "callback"
-required-features = ["prerecorded"]
+path = "examples/transcription/rest/callback.rs"
+required-features = ["listen"]
 
 [[example]]
 name = "make_prerecorded_request_builder"
-required-features = ["prerecorded"]
+path = "examples/transcription/rest/make_prerecorded_request_builder.rs"
+required-features = ["listen"]
+
+[[example]]
+name = "prerecorded_from_url"
+path = "examples/transcription/rest/prerecorded_from_url.rs"
+required-features = ["listen"]
+
+[[example]]
+name = "simple_stream"
+path = "examples/transcription/websocket/simple_stream.rs"
+required-features = ["listen"]
 
 [[example]]
 name = "microphone_stream"
-required-features = ["live"]
+path = "examples/transcription/websocket/microphone_stream.rs"
+required-features = ["listen"]
 
 [[example]]
-name = "prerecorded_from_url"
-required-features = ["prerecorded"]
+name = "text_to_speech_to_file"
+path = "examples/speak/rest/text_to_speech_to_file.rs"
+required-features = ["speak"]
 
 [[example]]
-name = "simple_stream"
-required-features = ["live"]
+name = "text_to_speech_to_stream"
+path = "examples/speak/rest/text_to_speech_to_stream.rs"
+required-features = ["speak"]

README.md

@@ -46,6 +46,12 @@ To make sure our community is safe for all, be sure to review and agree to our
 [Code of Conduct](./CODE_OF_CONDUCT.md). Then see the
 [Contributing Guidelines](./CONTRIBUTING.md) for more information.
 
+### Build the SDK
+
+```sh
+cargo build
+```
+
 ## Getting Help
 
 We love to hear from you so if you have questions, comments or find a bug in the

examples/README.md

@@ -0,0 +1,21 @@
+## Running Examples
+
+### Setting Env Vars
+
+```sh
+export FILENAME=./examples/audio/Bueller-Life-moves-pretty-fast.mp3
+```
+
+### Running the examples
+
+```sh
+cargo run --example prerecorded_from_url
+```
+
+```sh
+cargo run --example simple_stream
+```
+
+```sh
+cargo run --example advanced_stream
+```