blob: e1c86fdb5187047dd8f7b360dc5369657f12b9af [file] [log] [blame]
Bu Sun Kim715bd7f2019-06-14 16:50:42 -07001<html><body>
2<style>
3
4body, h1, h2, h3, div, span, p, pre, a {
5 margin: 0;
6 padding: 0;
7 border: 0;
8 font-weight: inherit;
9 font-style: inherit;
10 font-size: 100%;
11 font-family: inherit;
12 vertical-align: baseline;
13}
14
15body {
16 font-size: 13px;
17 padding: 1em;
18}
19
20h1 {
21 font-size: 26px;
22 margin-bottom: 1em;
23}
24
25h2 {
26 font-size: 24px;
27 margin-bottom: 1em;
28}
29
30h3 {
31 font-size: 20px;
32 margin-bottom: 1em;
33 margin-top: 1em;
34}
35
36pre, code {
37 line-height: 1.5;
38 font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
39}
40
41pre {
42 margin-top: 0.5em;
43}
44
45h1, h2, h3, p {
46 font-family: Arial, sans serif;
47}
48
49h1, h2, h3 {
50 border-bottom: solid #CCC 1px;
51}
52
53.toc_element {
54 margin-top: 0.5em;
55}
56
57.firstline {
58 margin-left: 2 em;
59}
60
61.method {
62 margin-top: 1em;
63 border: solid 1px #CCC;
64 padding: 1em;
65 background: #EEE;
66}
67
68.details {
69 font-weight: bold;
70 font-size: 14px;
71}
72
73</style>
74
75<h1><a href="texttospeech_v1.html">Cloud Text-to-Speech API</a> . <a href="texttospeech_v1.text.html">text</a></h1>
76<h2>Instance Methods</h2>
77<p class="toc_element">
Dan O'Mearadd494642020-05-01 07:42:23 -070078 <code><a href="#synthesize">synthesize(body=None, x__xgafv=None)</a></code></p>
Bu Sun Kim715bd7f2019-06-14 16:50:42 -070079<p class="firstline">Synthesizes speech synchronously: receive results after all text input</p>
80<h3>Method Details</h3>
81<div class="method">
Dan O'Mearadd494642020-05-01 07:42:23 -070082 <code class="details" id="synthesize">synthesize(body=None, x__xgafv=None)</code>
Bu Sun Kim715bd7f2019-06-14 16:50:42 -070083 <pre>Synthesizes speech synchronously: receive results after all text input
84has been processed.
85
86Args:
Dan O'Mearadd494642020-05-01 07:42:23 -070087 body: object, The request body.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -070088 The object takes the form of:
89
90{ # The top-level message sent by the client for the `SynthesizeSpeech` method.
91 "input": { # Contains text input to be synthesized. Either `text` or `ssml` must be # Required. The Synthesizer requires either plain text or SSML as input.
92 # supplied. Supplying both or neither returns
93 # google.rpc.Code.INVALID_ARGUMENT. The input size is limited to 5000
94 # characters.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -070095 "ssml": "A String", # The SSML document to be synthesized. The SSML document must be valid
96 # and well-formed. Otherwise the RPC will fail and return
97 # google.rpc.Code.INVALID_ARGUMENT. For more information, see
98 # [SSML](/speech/text-to-speech/docs/ssml).
Dan O'Mearadd494642020-05-01 07:42:23 -070099 "text": "A String", # The raw text to be synthesized.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700100 },
101 "voice": { # Description of which voice to use for a synthesis request. # Required. The desired voice of the synthesized audio.
Dan O'Mearadd494642020-05-01 07:42:23 -0700102 "ssmlGender": "A String", # The preferred gender of the voice. If not set, the service will
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700103 # choose a voice based on the other parameters such as language_code and
104 # name. Note that this is only a preference, not requirement; if a
105 # voice of the appropriate gender is not available, the synthesizer should
106 # substitute a voice with a different gender rather than failing the request.
Dan O'Mearadd494642020-05-01 07:42:23 -0700107 "languageCode": "A String", # Required. The language (and potentially also the region) of the voice expressed as a
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700108 # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag, e.g.
Dan O'Mearadd494642020-05-01 07:42:23 -0700109 # "en-US". This should not include a script tag (e.g. use
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700110 # "cmn-cn" rather than "cmn-Hant-cn"), because the script will be inferred
111 # from the input provided in the SynthesisInput. The TTS service
112 # will use this parameter to help choose an appropriate voice. Note that
113 # the TTS service may choose a voice with a slightly different language code
114 # than the one selected; it may substitute a different region
115 # (e.g. using en-US rather than en-CA if there isn't a Canadian voice
116 # available), or even a different language, e.g. using "nb" (Norwegian
117 # Bokmal) instead of "no" (Norwegian)".
Dan O'Mearadd494642020-05-01 07:42:23 -0700118 "name": "A String", # The name of the voice. If not set, the service will choose a
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700119 # voice based on the other parameters such as language_code and gender.
120 },
121 "audioConfig": { # Description of audio data to be synthesized. # Required. The configuration of the synthesized audio.
Dan O'Mearadd494642020-05-01 07:42:23 -0700122 "audioEncoding": "A String", # Required. The format of the audio byte stream.
123 "effectsProfileId": [ # Optional. Input only. An identifier which selects 'audio effects' profiles
124 # that are applied on (post synthesized) text to speech. Effects are applied
125 # on top of each other in the order they are given. See
126 # [audio
127 # profiles](https://cloud.google.com/text-to-speech/docs/audio-profiles) for
128 # current supported profile ids.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700129 "A String",
130 ],
Dan O'Mearadd494642020-05-01 07:42:23 -0700131 "sampleRateHertz": 42, # Optional. The synthesis sample rate (in hertz) for this audio. When this is
132 # specified in SynthesizeSpeechRequest, if this is different from the voice's
133 # natural sample rate, then the synthesizer will honor this request by
134 # converting to the desired sample rate (which might result in worse audio
135 # quality), unless the specified sample rate is not supported for the
136 # encoding chosen, in which case it will fail the request and return
137 # google.rpc.Code.INVALID_ARGUMENT.
138 "pitch": 3.14, # Optional. Input only. Speaking pitch, in the range [-20.0, 20.0]. 20 means
139 # increase 20 semitones from the original pitch. -20 means decrease 20
140 # semitones from the original pitch.
141 "speakingRate": 3.14, # Optional. Input only. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is
142 # the normal native speed supported by the specific voice. 2.0 is twice as
143 # fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
144 # speed. Any other values &lt; 0.25 or &gt; 4.0 will return an error.
145 "volumeGainDb": 3.14, # Optional. Input only. Volume gain (in dB) of the normal native volume
146 # supported by the specific voice, in the range [-96.0, 16.0]. If unset, or
147 # set to a value of 0.0 (dB), will play at normal native signal amplitude. A
148 # value of -6.0 (dB) will play at approximately half the amplitude of the
149 # normal native signal amplitude. A value of +6.0 (dB) will play at
150 # approximately twice the amplitude of the normal native signal amplitude.
151 # Strongly recommend not to exceed +10 (dB) as there's usually no effective
152 # increase in loudness for any value greater than that.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700153 },
154 }
155
156 x__xgafv: string, V1 error format.
157 Allowed values
158 1 - v1 error format
159 2 - v2 error format
160
161Returns:
162 An object of the form:
163
164 { # The message returned to the client by the `SynthesizeSpeech` method.
165 "audioContent": "A String", # The audio data bytes encoded as specified in the request, including the
Dan O'Mearadd494642020-05-01 07:42:23 -0700166 # header for encodings that are wrapped in containers (e.g. MP3, OGG_OPUS).
167 # For LINEAR16 audio, we include the WAV header. Note: as
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700168 # with all bytes fields, protobuffers use a pure binary representation,
169 # whereas JSON representations use base64.
170 }</pre>
171</div>
172
173</body></html>