You have up to 1000 free minutes of platform time per month on which to use it.įor other accounts, our TTS is charged per conversion, per minute with 15 second granularity. On a developer cloud account you can start using TTS straight away. Options are: reduced, moderate and strong.Įxamples: This is a level of emphasis, which can be used to highlight important information. Options are: silent, x-soft, soft, medium, loud and x-loud, a relative change (measured in Hz) e.g. Options are: x-slow, slow, medium, fast and x-fast,a relative change (measured in Hz) e.g. Options are: x-low, low, medium, high, x-high,a relative change (measured in Hz) e.g. Pitch can be used to set the pitch of speech. For the REST API please use the tts_voice setting.Įxamples: I'm using Amy instead of the default voice.Īllows the user to change the pitch, speed and volume of a segment of speech.Ĭommon optional parameters are: pitch, rate and volume. This SSML features is supported in the UAS API only. The supported voices for each TTS are listed above. Parameter name is required, specifying the voice to use. These are none, x-weak, weak, medium, strong and x-strong.Īllows the user to change the voice used. Strength sets the relative value of the pause. The length of a break may be up to 10 seconds in duration For example and set the break time to be three seconds and three milliseconds respectively. Time sets an absolute value for the pause. Optional arguments are time and strength. It is highly recommended that you test your application before deploying with a different TTS engine. Details of common tags can be found below. Polly and Cepstral both support a subset of SSML. As the length of the text is increased the generation time for the associated audio will also increase and, if is not a repeated phrase (and therefore may be cached) there will be a longer delay before the audio is played. The maximum length of the text to be converted is 1500 characters. Some characters are reserved so, if the text you need to say contains any of these, replace them as shown: Reserved Characterįor example, "Bill & Ben played in the garden" would be become "Bill & Ben played in the garden". Inserting recorded audio files (our APIs' play functions already allow file replay).We support the following Cepstral voices: With reference to that page, please bear in mind the following: For more detailed information, go to Cepstral SSML FAQ and scroll down to the 'Common Usage Examples'. For a summary of the SSML tags which may be used, see Common SSML tags below. Spanish Castile Female Polly Lucia NeuralĬepstral's website has a demo which allows you to select a voice and immediately hear how different text will sound - see Cepstral demos.Ĭepstral TTS supports a subset of the Speech Synthesis Markup Language (SSML), which can optionally be embedded within the text you supply to the say function. Portuguese Brazilian Female Polly Vitoria Neural Portuguese Portugal Female Polly Ines Neural Portuguese Brazilian Female Polly Camila Neural German Austria Female Polly Hannah Neural NameĬatalan Castile Female Polly Arlet NeuralĮnglish New Zealand Female Polly Aria NeuralĮnglish South Africa Female Polly Ayanda NeuralĮnglish Australia Female Polly Olivia Neuralįrench Canada Female Polly Gabrielle Neural No voices are available for this combination. For example, to set English US Female Polly Kimberly use the following SSML: ("I have something to say.") If you don't provide these tags your account's Default TTS voice will be used. You can also choose the TTS engine to use, via the optional acu-engine tag which, if provided, must be outermost in the string. In the UAS API, the Say methods support Speech Synthesis Markup Language (SSML) allowing you to change the way your text is spoken, for example, by choosing which voice you'd like to use using the voice tag. For example, to set English US Female Polly Kimberly use the following setting for tts_voice: "tts_voice" : "English US Female Polly Kimberly" You can choose a different voice by setting tts_voice to a Selector from the voice tables below. This defaults to the voice configured in your service. However, this cannot be used to select the voice used by TTS to say your text. In the REST API Play action, the text_to_say property supports Speech Synthesis Markup Language (SSML) allowing you to change the way your text is spoken. Aculab Cloud supports Amazon Polly and Cepstral Text To Speech (TTS) engines.
0 kommentar(er)
