README
¶
AzureTextToSpeech Client
This package provides a client for Azure's Cognitive Services (speech services) Text To Speech API. Users of the client
can specify the lanaguage (Region type), a string containing the desired text to speak as well as the gender (Gender type) in which the audiofile should be rendered. The library fetches the audio rendered in the format of your choice (see AudioOutput types for supported formats).
API documents of interest
- Text to speech Azure pricing details. Note there is a free tier available.
- Text to speech, speech services API specifications.
Requirements
A Cognitive Services (kind=Speech Services) API key is required to access the URL. This service can be enabled at the Azure portal.
Howto
The following will synthesize the string 64 BASIC BYTES FREE. READY., using the en-US locale, rending with a female voice. The output file format is a 16khz 32kbit single channel MP3 audio file.
import tts "github.com/jesseward/azuretexttospeech"
func main() {
# See TextToSpeechAPI and TokenRefreshAPI types for list of endpoints and regions.
azureSpeech, _ := tts.New("YOUR-API-KEY", tts.RegionEastUS)
ctx := context.Background()
payload, _ := az.SynthesizeWithContext(
ctx,
"64 BASIC BYTES FREE. READY.",
tts.LocaleEnUS, // Region type
tts.GenderFemale, // Gender type
tts.Audio16khz32kbitrateMonoMp3) // AudioOutput type
// the response `payload` is your byte array containing audio data.
}
Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
var MapAudioFileExtensions = map[string]string{
"RAW16khz16bitMonoPCM": "raw",
"RAW24khz16bitMonoPCM": "raw",
"RAW48khz16bitMonoPCM": "raw",
"RAW8khz8bitMonoMulaw": "raw",
"RAW8khz8bitMonoAlaw": "raw",
"AUDIO16khz32kbitrateMonoMP3": "mp3",
"AUDIO16khz128kbitrateMonoMP3": "mp3",
"AUDIO24khz96kbitrateMonoMP3": "mp3",
"AUDIO48khz96kbitrateMonoMP3": "mp3",
"RAW16khz16bitMonoTruesilk": "raw",
"WEBM16khz16bitMonoOpus": "opus",
"OGG16khz16bitMonoOpus": "opus",
"OGG48khz16bitMonoOpus": "opus",
"RIFF16khz16bitMonoPCM": "wav",
"RIFF24khz16bitMonoPCM": "wav",
"RIFF48khz16bitMonoPCM": "wav",
"RIFF8khz8bitMonoMulaw": "wav",
"RIFF8khz8bitMonoAlaw": "wav",
"AUDIO16khz64kbitrateMonoMP3": "mp3",
"AUDIO24khz48kbitrateMonoMP3": "mp3",
"AUDIO24khz160kbitrateMonoMP3": "mp3",
"AUDIO48khz192kbitrateMonoMP3": "mp3",
"RAW24khz16bitMonoTruesilk": "raw",
"WEBM24khz16bitMonoOpus": "webm",
"OGG24khz16bitMonoOpus": "ogg",
}
var MapAudioToFormatid = map[string]AudioOutput{ "RAW16khz16bitMonoPCM": RAW16khz16bitMonoPCM, "RAW24khz16bitMonoPCM": RAW24khz16bitMonoPCM, "RAW48khz16bitMonoPCM": RAW48khz16bitMonoPCM, "RAW8khz8bitMonoMulaw": RAW8khz8bitMonoMulaw, "RAW8khz8bitMonoAlaw": RAW8khz8bitMonoAlaw, "AUDIO16khz32kbitrateMonoMP3": AUDIO16khz32kbitrateMonoMP3, "AUDIO16khz128kbitrateMonoMP3": AUDIO16khz128kbitrateMonoMP3, "AUDIO24khz96kbitrateMonoMP3": AUDIO24khz96kbitrateMonoMP3, "AUDIO48khz96kbitrateMonoMP3": AUDIO48khz96kbitrateMonoMP3, "RAW16khz16bitMonoTruesilk": RAW16khz16bitMonoTruesilk, "WEBM16khz16bitMonoOpus": WEBM16khz16bitMonoOpus, "OGG16khz16bitMonoOpus": OGG16khz16bitMonoOpus, "OGG48khz16bitMonoOpus": OGG48khz16bitMonoOpus, "RIFF16khz16bitMonoPCM": RIFF16khz16bitMonoPCM, "RIFF24khz16bitMonoPCM": RIFF24khz16bitMonoPCM, "RIFF48khz16bitMonoPCM": RIFF48khz16bitMonoPCM, "RIFF8khz8bitMonoMulaw": RIFF8khz8bitMonoMulaw, "RIFF8khz8bitMonoAlaw": RIFF8khz8bitMonoAlaw, "AUDIO16khz64kbitrateMonoMP3": AUDIO16khz64kbitrateMonoMP3, "AUDIO24khz48kbitrateMonoMP3": AUDIO24khz48kbitrateMonoMP3, "AUDIO24khz160kbitrateMonoMP3": AUDIO24khz160kbitrateMonoMP3, "AUDIO48khz192kbitrateMonoMP3": AUDIO48khz192kbitrateMonoMP3, "RAW24khz16bitMonoTruesilk": RAW24khz16bitMonoTruesilk, "WEBM24khz16bitMonoOpus": WEBM24khz16bitMonoOpus, "OGG24khz16bitMonoOpus": OGG24khz16bitMonoOpus, }
Functions ¶
func GenderStrings ¶
func GenderStrings() []string
GenderStrings returns a slice of all String values of the enum
func LocaleStrings ¶
func LocaleStrings() []string
LocaleStrings returns a slice of all String values of the enum
Types ¶
type AudioOutput ¶
type AudioOutput int
const ( RAW16khz16bitMonoPCM AudioOutput = iota RAW24khz16bitMonoPCM RAW48khz16bitMonoPCM RAW8khz8bitMonoMulaw RAW8khz8bitMonoAlaw AUDIO16khz32kbitrateMonoMP3 AUDIO16khz128kbitrateMonoMP3 AUDIO24khz96kbitrateMonoMP3 AUDIO48khz96kbitrateMonoMP3 RAW16khz16bitMonoTruesilk WEBM16khz16bitMonoOpus OGG16khz16bitMonoOpus OGG48khz16bitMonoOpus RIFF16khz16bitMonoPCM RIFF24khz16bitMonoPCM RIFF48khz16bitMonoPCM RIFF8khz8bitMonoMulaw RIFF8khz8bitMonoAlaw AUDIO16khz64kbitrateMonoMP3 AUDIO24khz48kbitrateMonoMP3 AUDIO24khz160kbitrateMonoMP3 AUDIO48khz192kbitrateMonoMP3 RAW24khz16bitMonoTruesilk WEBM24khz16bitMonoOpus OGG24khz16bitMonoOpus )
func (AudioOutput) String ¶
func (a AudioOutput) String() string
type AzureCSTextToSpeech ¶
type AzureCSTextToSpeech struct {
RegionVoiceMap RegionVoiceMap
SubscriptionKey string // API key for Azure's Congnitive Speech services
TokenRefreshDoneCh chan bool // channel to stop the token refresh goroutine.
HttpProxy string
// contains filtered or unexported fields
}
AzureCSTextToSpeech stores configuration and state information for the TTS client.
func New ¶
func New(subscriptionKey string, region Region, proxy string) (*AzureCSTextToSpeech, error)
New returns an AzureCSTextToSpeech object.
func (*AzureCSTextToSpeech) Synthesize ¶
func (az *AzureCSTextToSpeech) Synthesize(speechText string, locale Locale, name, pitch, rate string, audioOutput AudioOutput) ([]byte, error)
Synthesize directs to SynthesizeWithContext. A new context.Withtimeout is created with the timeout as defined by synthesizeActionTimeout
func (*AzureCSTextToSpeech) SynthesizeWithContext ¶
func (az *AzureCSTextToSpeech) SynthesizeWithContext(ctx context.Context, speechText string, locale Locale, name, pitch, rate string, audioOutput AudioOutput) ([]byte, error)
SynthesizeWithContext returns a bytestream of the rendered text-to-speech in the target audio format. `speechText` is the string of text in which a user wishes to Synthesize, `region` is the language/locale, `gender` is the desired output voice and `audioOutput` captures the audio format.
type ExtendedPropertyMap ¶
type ExtendedPropertyMap struct {
IsHighQuality48K string `json:"IsHighQuality48K,omitempty"`
}
type Gender ¶
type Gender int
Gender type for the digitized language
const ( // GenderMale , GenderFemale are the static Gender constants for digitized voices. // See Gender in https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support#standard-voices for breakdown GenderMale Gender = iota // Male GenderFemale // Female )
func GenderString ¶
GenderString retrieves an enum value from the enum constants string name. Throws an error if the param is not part of the enum.
func (Gender) IsAGender ¶
IsAGender returns "true" if the value is listed in the enum definition. "false" otherwise
func (Gender) MarshalJSON ¶
MarshalJSON implements the json.Marshaler interface for Gender
func (*Gender) UnmarshalJSON ¶
UnmarshalJSON implements the json.Unmarshaler interface for Gender
type Locale ¶
type Locale int
Locale references the language or locale for text-to-speech. See "locale" in https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support#standard-voices
const ( LocaleafZA Locale = iota //af-ZA LocaleamET //am-ET LocalearAE //ar-AE LocalearBH //ar-BH LocalearDZ //ar-DZ LocalearEG //ar-EG LocalearIQ //ar-IQ LocalearJO //ar-JO LocalearKW //ar-KW LocalearLY //ar-LY LocalearMA //ar-MA LocalearQA //ar-QA LocalearSA //ar-SA LocalearSY //ar-SY LocalearTN //ar-TN LocalearYE //ar-YE LocalebgBG //bg-BG LocalebnBD //bn-BD LocalecaES //ca-ES LocalecsCZ //cs-CZ LocalecyGB //cy-GB LocaledaDK //da-DK LocaledeAT //de-AT LocaledeCH // de-CH LocaledeDE // de-DE LocaleelGR // el-GR LocaleenAU // en-AU LocaleenCA // en-CA LocaleenGB // en-GB LocaleenHK // en-HK LocaleenIE // en-IE LocaleenIN // en-IN LocaleenKE // en-KE LocaleenNG // en-NG LocaleenNZ // en-NZ LocaleenPH // en-PH LocaleenSG // en-SG LocaleenTZ // en-TZ LocaleenUS // en-US LocaleenZA // en-ZA LocaleesAR // es-AR LocaleesBO // es-BO LocaleesCL // es-CL LocaleesCO // es-CO LocaleesCR // es-CR LocaleesCU // es-CU LocaleesDO // es-DO LocaleesEC // es-EC LocaleesES // es-ES LocaleesGQ // es-GQ LocaleesGT // es-GT LocaleesHN // es-HN LocaleesMX // es-MX LocaleesNI // es-NI LocaleesPA // es-PA LocaleesPE // es-PE LocaleesPR // es-PR LocaleesPY // es-PY LocaleesSV // es-SV LocaleesUS // es-US LocaleesUY // es-UY LocaleesVE // es-VE LocaleetEE // et-EE LocalefaIR // fa-IR LocalefiFI // fi-FI LocalefilPH // fil-PH LocalefrBE // fr-BE LocalefrCA // fr-CA LocalefrCH // fr-CH LocalefrFR // fr-FR LocalegaIE // ga-IE LocaleglES // gl-ES LocaleguIN // gu-IN LocaleheIL // he-IL LocalehiIN // hi-IN LocalehrHR // hr-HR LocalehuHU // hu-HU LocaleidID // id-ID LocaleitIT // it-IT LocalejaJP // ja-JP LocalejvID // jv-ID LocalekmKH // km-KH LocalekoKR // ko-KR LocaleltLT // lt-LT LocalelvLV // lv-LV LocalemrIN // mr-IN LocalemsMY // ms-MY LocalemtMT // mt-MT LocalemyMM // my-MM LocalenbNO // nb-NO LocalenlBE // nl-BE LocalenlNL // nl-NL LocaleplPL // pl-PL LocaleptBR // pt-BR LocaleptPT // pt-PT LocaleroRO // ro-RO LocaleruRU // ru-RU LocaleskSK // sk-SK LocaleslSI // sl-SI LocalesoSO // so-SO LocalesuID // su-ID LocalesvSE // sv-SE LocaleswKE // sw-KE LocaleswTZ // sw-TZ LocaletaIN // ta-IN LocaletaLK // ta-LK LocaletaSG // ta-SG LocaleteIN // te-IN LocalethTH // th-TH LocaletrTR // tr-TR LocaleukUA // uk-UA LocaleurIN // ur-IN LocaleurPK // ur-PK LocaleuzUZ // uz-UZ LocaleviVN // vi-VN LocalezhCN // zh-CN LocalezhHK // zh-HK LocalezhTW // zh-TW LocalezuZA // zu-ZA )
func LocaleString ¶
LocaleString retrieves an enum value from the enum constants string name. Throws an error if the param is not part of the enum.
func (Locale) IsALocale ¶
IsALocale returns "true" if the value is listed in the enum definition. "false" otherwise
func (Locale) MarshalJSON ¶
MarshalJSON implements the json.Marshaler interface for Locale
func (*Locale) UnmarshalJSON ¶
UnmarshalJSON implements the json.Unmarshaler interface for Locale
type Region ¶
type Region int
Region references the locations of the availability of standard voices. See https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/regions#standard-voices
const ( // Azure regions and their endpoints that support the Text To Speech service. RegionAustraliaEast Region = iota RegionBrazilSouth RegionCanadaCentral RegionCentralUS RegionEastAsia RegionEastUS RegionEastUS2 RegionFranceCentral RegionIndiaCentral RegionJapanEast RegionJapanWest RegionKoreaCentral RegionNorthCentralUS RegionNorthEurope RegionSouthCentralUS RegionSoutheastAsia RegionUKSouth RegionWestEurope RegionWestUS RegionWestUS2 )
type RegionVoiceMap ¶
type RegionVoiceMap map[supportedVoices]string
Source Files
Directories