1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
/// Additional options for speech synthesis
pub mod synthesis;
/// Defines voices available in the Text to Speech service.
pub mod voices;
use std::str::FromStr;
use hyper::{
client::HttpConnector,
header::{self, HeaderName, HeaderValue},
Body, Client, HeaderMap, Method, Request,
};
use hyper_tls::HttpsConnector;
use serde::Deserialize;
use url::Url;
use crate::{
core::services::ConfigService,
core::IamAuthenticator,
tts::{
synthesis::map_audio_format,
voices::{def::Voices, voice_map},
},
};
use self::{
synthesis::AudioFormats,
voices::{def::Voice, AvailableVoices},
};
/// The format to use when getting pronunciations.
#[derive(Debug)]
pub enum PhonemeFormat {
/// `ibm`
IBM,
/// `ipa`
IPA,
}
impl Default for PhonemeFormat {
/// `ipa`
fn default() -> Self {
Self::IPA
}
}
/// Pronunciation options to be passed to [pronunciation](TextToSpeech::pronunciation).
pub struct PronunciationOptions<'a> {
/// The [PhonemeFormat](self::PhonemeFormat) to be used in pronunciation.
pub format: PhonemeFormat,
/// The text to be used in pronunciation.
pub text: &'a str,
/// The voice (ideally of the same language) to use in getting pronunciation [Voices](voices::AvailableVoices)
pub voice: AvailableVoices,
}
#[derive(Deserialize)]
struct Pronunciation {
pronunciation: String,
}
impl<'a> PronunciationOptions<'a> {
/// Creates a new pronunciation definition.
///
/// # Arguments
///
/// * `format` - the [format](self::PhonemeFormat) to be used in the request for pronunciation.
/// * `text` - pronunciation query.
/// * `voice` - the [AvailableVoices](voices::AvailableVoices) to use, ideally of the same language as the query.
///
/// # Examples
///
/// ```
/// # use ibm_watson::tts::PronunciationOptions;
/// # use ibm_watson::tts::voices::AvailableVoices;
/// # use ibm_watson::tts::PhonemeFormat;
/// let mut options = PronunciationOptions::new(
/// PhonemeFormat::default(),
/// "aujourd-hui",
/// AvailableVoices::fr_FR_Renee,
/// );
/// ```
pub fn new(format: PhonemeFormat, text: &'a str, voice: AvailableVoices) -> Self {
Self {
format,
text,
voice,
}
}
/// Updates the pronunciation query.
///
/// # Arguments
///
/// * `text` - new pronunciation query.
///
/// # Examples
///
/// ```
/// # use ibm_watson::tts::PronunciationOptions;
/// # use ibm_watson::tts::voices::AvailableVoices;
/// # use ibm_watson::tts::PhonemeFormat;
/// # let mut options = PronunciationOptions::new(
/// # PhonemeFormat::default(),
/// # "aujourd-hui",
/// # AvailableVoices::fr_FR_Renee,
/// # );
/// options.set_text("bonjour");
/// ```
pub fn set_text(&mut self, text: &'a str) {
self.text = text;
}
/// Updates the voice used in pronunciation query.
///
/// # Arguments
///
/// * `voice` - [AvailableVoices](voices::AvailableVoices) to use in getting pronunciation.
///
/// # Examples
///
/// ```
/// # use ibm_watson::tts::PronunciationOptions;
/// # use ibm_watson::tts::voices::AvailableVoices;
/// # use ibm_watson::tts::PhonemeFormat;
/// # let mut options = PronunciationOptions::new(
/// # PhonemeFormat::default(),
/// # "aujourd-hui",
/// # AvailableVoices::fr_FR_NicolasV3,
/// # );
/// options.set_voice(AvailableVoices::fr_FR_NicolasV3);
/// ```
pub fn set_voice(&mut self, voice: AvailableVoices) {
self.voice = voice;
}
/// Updates the format used in pronunciation query.
///
/// # Arguments
///
/// * `format` - [PhonemeFormat](self::PhonemeFormat)
///
/// # Examples
///
/// ```
/// # use ibm_watson::tts::PronunciationOptions;
/// # use ibm_watson::tts::voices::AvailableVoices;
/// # use ibm_watson::tts::PhonemeFormat;
/// # let mut options = PronunciationOptions::new(
/// # PhonemeFormat::default(),
/// # "aujourd-hui",
/// # AvailableVoices::fr_FR_NicolasV3,
/// # );
/// options.set_format(PhonemeFormat::IBM);
/// ```
pub fn set_format(&mut self, format: PhonemeFormat) {
self.format = format;
}
}
/// Defines text to speech options.
pub struct TextToSpeech {
pub(crate) service_url: String,
pub(crate) headers: HeaderMap,
pub(crate) client: Client<HttpsConnector<HttpConnector>>,
pub(crate) voice: AvailableVoices,
}
impl TextToSpeech {
/// Creates a new text to speech options and sets headers based on [IamAuthenticator](super::core::IamAuthenticator).
///
/// # Arguments
///
/// * `auth` - a reference to [IamAuthenticator](super::core::IamAuthenticator) to use, ideally of the same language as the query.
/// * `service_url` - your IBM Watson TTS endpoint.
///
/// # Examples
///
/// ```
/// # use ibm_watson::core::IamAuthenticator;
/// # use ibm_watson::tts::TextToSpeech;
/// let tts_service_url = String::from("https://my.service.url/foobar");
/// let auth = IamAuthenticator::new("{myapikey}");
/// let mut tts = TextToSpeech::new(
/// &auth,
/// tts_service_url,
/// );
/// ```
pub fn new(auth: &IamAuthenticator, service_url: String) -> Self {
let mut headers = HeaderMap::default();
headers.insert(
header::AUTHORIZATION,
HeaderValue::from_str(auth.apikey()).expect("Invalid Header Value"),
);
headers.insert(
HeaderName::from_str("X-Watson-Learning-Opt-Out")
.expect("Invalid HeaderName 'X-Watson-Learning-Opt-Out'"),
HeaderValue::from_str("true").expect("Failed to Disable IBM Data Collection"),
);
Self {
headers,
service_url,
client: Client::builder().build::<_, hyper::Body>(HttpsConnector::new()),
voice: AvailableVoices::default(),
}
}
/// Changes the voice (from the default).
///
/// # Arguments
///
/// * `voice` - [AvailableVoices](voices::AvailableVoices)
///
/// # Examples
///
/// ```
/// # use ibm_watson::core::IamAuthenticator;
/// # use ibm_watson::tts::TextToSpeech;
/// # use ibm_watson::tts::voices::AvailableVoices;
/// # let tts_service_url = String::from("https://my.service.url/foobar");
/// # let auth = IamAuthenticator::new("{myapikey}");
/// # let mut tts = TextToSpeech::new(
/// # &auth,
/// # tts_service_url,
/// # );
/// tts.set_voice(AvailableVoices::en_US_OliviaV3);
/// ```
pub fn set_voice(&mut self, voice: AvailableVoices) {
self.voice = voice;
}
/// Returns the `String` equivalent of the current [AvailableVoices](voices::AvailableVoices) set on the current options.
///
/// # Examples
///
/// ```
/// # use ibm_watson::core::IamAuthenticator;
/// # use ibm_watson::tts::TextToSpeech;
/// # use ibm_watson::tts::voices::AvailableVoices;
/// # let tts_service_url = String::from("https://my.service.url/foobar");
/// # let auth = IamAuthenticator::new("{myapikey}");
/// # let mut tts = TextToSpeech::new(
/// # &auth,
/// # tts_service_url,
/// # );
/// println!("{}", tts.current_voice());
/// ```
pub fn current_voice(&self) -> String {
voice_map(self.voice).to_owned()
}
/// Returns a `Vec` of all the [Voices](voices::def::Voice) IBM Watson has.
///
/// # Examples
///
/// ```
/// # use ibm_watson::core::IamAuthenticator;
/// # use ibm_watson::tts::TextToSpeech;
/// # use ibm_watson::tts::voices::AvailableVoices;
/// # use std::error::Error;
/// # async fn foo()->Result<(),Box<dyn Error>> {
/// # let tts_service_url = String::from("https://my.service.url/foobar");
/// # let auth = IamAuthenticator::new("{myapikey}");
/// # let tts = TextToSpeech::new(
/// # &auth,
/// # tts_service_url,
/// # );
/// let voices = tts.voices().await?;
/// for i in &voices {
/// println!("{}", i.name);
/// }
/// # Ok(())
/// # }
/// ```
pub async fn voices(&self) -> Result<Vec<Voice>, anyhow::Error> {
let mut request = self.template_request();
*request.method_mut() = Method::GET;
let uri = format!("{}/v1/voices", &self.service_url);
*request.uri_mut() = uri.parse()?;
*request.body_mut() = Body::empty();
let res = self.client.request(request).await?;
assert_eq!(res.status(), hyper::StatusCode::OK);
let bytes = hyper::body::to_bytes(res.into_body()).await?;
let root: Voices = serde_json::from_slice(bytes.to_vec().as_slice())?;
Ok(root.voices)
}
/// Returns [details](voices::def::Voice) about a selected voice from [](voices::AvailableVoices)
///
/// # Examples
/// ```
/// # use ibm_watson::core::IamAuthenticator;
/// # use ibm_watson::tts::TextToSpeech;
/// # use ibm_watson::tts::voices::AvailableVoices;
/// # use std::error::Error;
/// # async fn foo()->Result<(),Box<dyn Error>> {
/// # let tts_service_url = String::from("https://my.service.url/foobar");
/// # let auth = IamAuthenticator::new("{myapikey}");
/// # let tts = TextToSpeech::new(
/// # &auth,
/// # tts_service_url,
/// # );
/// let olivia = tts.voice(AvailableVoices::en_US_OliviaV3).await?;
/// println!("{:#?}", olivia);
/// # Ok(())
/// # }
/// ```
pub async fn voice(&self, voice: AvailableVoices) -> Result<Voice, anyhow::Error> {
let mut request = self.template_request();
*request.method_mut() = Method::GET;
let uri = format!("{}/v1/voices/{}", &self.service_url, voice_map(voice));
*request.uri_mut() = uri.parse()?;
*request.body_mut() = Body::empty();
let res = self.client.request(request).await?;
assert_eq!(res.status(), hyper::StatusCode::OK);
let bytes = hyper::body::to_bytes(res.into_body()).await?;
let root: Voice = serde_json::from_slice(bytes.to_vec().as_slice())?;
Ok(root)
}
/// Returns a stream of bytes containing synthesised text.
///
/// # Arguments
///
/// * `utterance` - text to synthesise.
/// * `format` - audio [format](synthesis::AudioFormats) to return.
///
/// # Examples
/// ```
/// # use ibm_watson::core::IamAuthenticator;
/// # use ibm_watson::tts::TextToSpeech;
/// # use ibm_watson::tts::voices::AvailableVoices;
/// # use std::error::Error;
/// # use ibm_watson::tts::synthesis::AudioFormats;
/// # async fn foo()->Result<(),Box<dyn Error>> {
/// # let tts_service_url = String::from("https://my.service.url/foobar");
/// # let auth = IamAuthenticator::new("{myapikey}");
/// # let mut tts = TextToSpeech::new(
/// # &auth,
/// # tts_service_url,
/// # );
/// let synth_bytes = tts.synthesise_text(
/// "This is just fantastic",
/// AudioFormats::default()
/// ).await?;
/// tts.set_voice(AvailableVoices::en_US_LisaV3);
/// let synth_bytes = tts.synthesise_text(
/// "I have changed the voice",
/// AudioFormats::AudioWav
/// ).await?;
/// # Ok(())
/// # }
/// ```
pub async fn synthesise_text(
&self,
utterance: &str,
format: AudioFormats,
) -> Result<hyper::body::Bytes, anyhow::Error> {
let mut url = Url::parse(&self.service_url)?;
url.set_path("v1/synthesize");
let accept = map_audio_format(format);
let mut request = self.template_request();
url.set_query(Some(format!("accept={}", accept).as_str()));
let mut stub: String = url.into();
stub = format!("{}&text={}", stub, utterance);
stub = Url::parse(&stub)?.to_string();
*request.method_mut() = Method::GET;
*request.uri_mut() = format!("{}&voice={}", stub, voice_map(self.voice)).parse()?;
let res = self.client.request(request).await?;
assert_eq!(res.status(), hyper::StatusCode::OK);
let bytes = hyper::body::to_bytes(res.into_body()).await?;
Ok(bytes)
}
/// Gets the phonetic pronunciation for the specified word. You can request the pronunciation for a specific format. You can also request the pronunciation for a specific voice to see the default translation for the language of that voice or for a specific custom model to see the translation for that model.
///
/// # Arguments
///
/// * `utterance` - text to synthesise.
/// * `format` - audio [format](synthesis::AudioFormats) to return.
///
/// # Examples
/// ```
/// # use ibm_watson::tts::PronunciationOptions;
/// # use ibm_watson::tts::voices::AvailableVoices;
/// # use ibm_watson::tts::PhonemeFormat;
/// # use ibm_watson::core::IamAuthenticator;
/// # use ibm_watson::tts::TextToSpeech;
/// # use std::error::Error;
/// # use ibm_watson::tts::synthesis::AudioFormats;
/// # async fn foo()->Result<(),Box<dyn Error>> {
/// # let tts_service_url = String::from("https://my.service.url/foobar");
/// # let auth = IamAuthenticator::new("{myapikey}");
/// # let mut tts = TextToSpeech::new(
/// # &auth,
/// # tts_service_url,
/// # );
/// let options = PronunciationOptions::new(
/// PhonemeFormat::default(),
/// "ça va",
/// AvailableVoices::fr_FR_Renee,
/// );
/// let pronunciation = tts.pronunciation(&options).await?;
/// println!("{}", pronunciation);
/// # Ok(())
/// # }
/// ```
pub async fn pronunciation<'a>(
&self,
options: &PronunciationOptions<'a>,
) -> Result<String, anyhow::Error> {
let mut url = Url::parse(&self.service_url)?;
url.set_path("v1/pronunciation");
let mut request = self.template_request();
url.set_query(Some(format!("text={}", options.text).as_str()));
let mut stub: String = url.into();
stub = format!(
"{}&format={}",
stub,
match options.format {
PhonemeFormat::IBM => "ibm",
PhonemeFormat::IPA => "ipa",
}
);
*request.method_mut() = Method::GET;
*request.uri_mut() = format!("{}&voice={}", stub, voice_map(options.voice)).parse()?;
let res = self.client.request(request).await?;
assert_eq!(res.status(), hyper::StatusCode::OK);
let bytes = hyper::body::to_bytes(res.into_body()).await?;
let root: Pronunciation = serde_json::from_slice(bytes.to_vec().as_slice())?;
Ok(root.pronunciation)
}
fn template_request(&self) -> Request<Body> {
let mut request = Request::default();
*request.headers_mut() = self.headers.clone();
request
}
}
impl ConfigService for TextToSpeech {
fn set_service_url(&mut self, service_url: String) {
self.service_url = service_url;
}
fn set_default_headers(
&mut self,
headers: std::collections::HashMap<String, String>,
) -> Result<(), anyhow::Error> {
for (key, value) in &headers {
self.headers
.insert(HeaderName::from_str(&key)?, HeaderValue::from_str(&value)?);
}
Ok(())
}
fn enable_ibm_data_collection(&mut self) {
self.headers.insert(
HeaderName::from_str("X-Watson-Learning-Opt-Out")
.expect("Invalid HeaderName 'X-Watson-Learning-Opt-Out'"),
HeaderValue::from_str("false").expect("Failed to Enable IBM Data Collection"),
);
}
fn disable_ibm_data_collection(&mut self) {
self.headers.insert(
HeaderName::from_str("X-Watson-Learning-Opt-Out")
.expect("Invalid HeaderName 'X-Watson-Learning-Opt-Out'"),
HeaderValue::from_str("true").expect("Failed to Disable IBM Data Collection"),
);
}
}
