JUMP TOPlay.ht APIGetting Started With PlayHT's APIPlayHT On-Prem⚡️ Realtime StreamingNodejs SDK Audio StreamingPython SDK Audio StreamingREST API Audio StreamingStream Audio From TextpostTechniques to guarantee the lowest latencyInput and Output Streaming with chatGPT (or any LLM)Audio streaming with Twilio💬 Async text to SPEECHGenerating Your First AudioGenerate Audio From TextpostGet Text-To-Speech Job Dataget📚 GuidesAuthenticationSupported Voice ModelsOn-Prem for AWSOn-Prem for Google Cloud🤖 sdkNode.jsPython🗣️ VoicesList PlayHT Voicesget🗪 voice cloningCreate Instant Voice Clone (via file upload)postCreate Instant Voice Clone (via file URL)postHigh-Fidelity CloningList Cloned VoicesgetDelete Cloned Voicesdelete🕒 TimestampsGet Timestamps From SpeechTimestamp From AudiopostGet Transcription Job Dataget⚙️ AdvancedWebhooksRate Limits🏛️ StandardStandard & Premium VoicesConvert Plain Text To SpeechpostConvert SSML To SpeechpostGet Conversion Job StatusgetGet Available Voicesget💔 DeprecatedDeprecatedList Cloned VoicesgetConvert Text To SpeechpostGet Available VoicesgetPowered by Convert Text To Speechpost deprecatedhttps://api.play.ht/api/v1/convert//⚠️DEPRECATEDPlease use the generate audio from text endpoint instead. This endpoint is used to trigger text to speech conversion. Which version should you use? If you are using a Standard & Premium voice (for instance, your voice look like en-US-JennyNeural), you must use the Convert TTS Standard & Premium Voices endpoint. If you are using a PlayHT voice use the Generate Audio endpoint. The request body should contain the text to be converted to speech, along with the voice to be used for the conversion. The response will contain a URL to the audio file generated by the conversion. Use the transcriptionId in the response to check the conversion status in the Get Article Conversion Status endpoint.