Text-to-Speech

Usage Instructions

Generate natural-sounding speech from text using state-of-the-art AI voices from OpenAI, Deepgram, ElevenLabs, Cartesia, Google Cloud, Azure, and PlayHT. Supports multiple voices, languages, and audio formats.

Tools

`tts_openai`

Convert text to speech using OpenAI TTS models

Input

Parameter	Type	Required	Description
`text`	string	Yes	The text to convert to speech
`apiKey`	string	Yes	OpenAI API key
`model`	string	No	TTS model to use (tts-1, tts-1-hd, or gpt-4o-mini-tts)
`voice`	string	No	Voice to use (alloy, ash, ballad, cedar, coral, echo, marin, sage, shimmer, verse)
`responseFormat`	string	No	Audio format (mp3, opus, aac, flac, wav, pcm)
`speed`	number	No	Speech speed (0.25 to 4.0, default: 1.0)

Output

Parameter	Type	Description
`audioUrl`	string	URL to the generated audio file
`audioFile`	file	Generated audio file object
`duration`	number	Audio duration in seconds
`characterCount`	number	Number of characters processed
`format`	string	Audio format
`provider`	string	TTS provider used

`tts_deepgram`

Convert text to speech using Deepgram Aura

Input

Parameter	Type	Required	Description
`text`	string	Yes	The text to convert to speech
`apiKey`	string	Yes	Deepgram API key
`model`	string	No	Deepgram model/voice (e.g., aura-asteria-en, aura-luna-en)
`voice`	string	No	Voice identifier (alternative to model param)
`encoding`	string	No	Audio encoding (linear16, mp3, opus, aac, flac)
`sampleRate`	number	No	Sample rate (8000, 16000, 24000, 48000)
`bitRate`	number	No	Bit rate for compressed formats
`container`	string	No	Container format (none, wav, ogg)

Output

Parameter	Type	Description
`audioUrl`	string	URL to the generated audio file
`audioFile`	file	Generated audio file object
`duration`	number	Audio duration in seconds
`characterCount`	number	Number of characters processed
`format`	string	Audio format
`provider`	string	TTS provider used

`tts_elevenlabs`

Convert text to speech using ElevenLabs voices

Input

Parameter	Type	Required	Description
`text`	string	Yes	The text to convert to speech
`voiceId`	string	Yes	The ID of the voice to use
`apiKey`	string	Yes	ElevenLabs API key
`modelId`	string	No	Model to use (e.g., eleven_monolingual_v1, eleven_turbo_v2_5, eleven_flash_v2_5)
`stability`	number	No	Voice stability (0.0 to 1.0, default: 0.5)
`similarityBoost`	number	No	Similarity boost (0.0 to 1.0, default: 0.8)
`style`	number	No	Style exaggeration (0.0 to 1.0)
`useSpeakerBoost`	boolean	No	Use speaker boost (default: true)

Output

Parameter	Type	Description
`audioUrl`	string	URL to the generated audio file
`audioFile`	file	Generated audio file object
`duration`	number	Audio duration in seconds
`characterCount`	number	Number of characters processed
`format`	string	Audio format
`provider`	string	TTS provider used

`tts_cartesia`

Convert text to speech using Cartesia Sonic (ultra-low latency)

Input

Parameter	Type	Required	Description
`text`	string	Yes	The text to convert to speech
`apiKey`	string	Yes	Cartesia API key
`modelId`	string	No	Model ID (sonic-english, sonic-multilingual)
`voice`	string	No	Voice ID or embedding
`language`	string	No	Language code (en, es, fr, de, it, pt, etc.)
`outputFormat`	json	No	Output format configuration (container, encoding, sampleRate)
`speed`	number	No	Speed multiplier
`emotion`	array	No	Emotion tags for Sonic-3 (e.g., ['positivity:high'])

Output

Parameter	Type	Description
`audioUrl`	string	URL to the generated audio file
`audioFile`	file	Generated audio file object
`duration`	number	Audio duration in seconds
`characterCount`	number	Number of characters processed
`format`	string	Audio format
`provider`	string	TTS provider used

`tts_google`

Convert text to speech using Google Cloud Text-to-Speech

Input

Parameter	Type	Required	Description
`text`	string	Yes	The text to convert to speech
`apiKey`	string	Yes	Google Cloud API key
`voiceId`	string	No	Voice ID (e.g., en-US-Neural2-A, en-US-Wavenet-D)
`languageCode`	string	Yes	Language code (e.g., en-US, es-ES, fr-FR)
`gender`	string	No	Voice gender (MALE, FEMALE, NEUTRAL)
`audioEncoding`	string	No	Audio encoding (LINEAR16, MP3, OGG_OPUS, MULAW, ALAW)
`speakingRate`	number	No	Speaking rate (0.25 to 2.0, default: 1.0)
`pitch`	number	No	Voice pitch (-20.0 to 20.0, default: 0.0)
`volumeGainDb`	number	No	Volume gain in dB (-96.0 to 16.0)
`sampleRateHertz`	number	No	Sample rate in Hz
`effectsProfileId`	array	No	Effects profile (e.g., ['headphone-class-device'])

Output

Parameter	Type	Description
`audioUrl`	string	URL to the generated audio file
`audioFile`	file	Generated audio file object
`duration`	number	Audio duration in seconds
`characterCount`	number	Number of characters processed
`format`	string	Audio format
`provider`	string	TTS provider used

`tts_azure`

Convert text to speech using Azure Cognitive Services

Input

Parameter	Type	Required	Description
`text`	string	Yes	The text to convert to speech
`apiKey`	string	Yes	Azure Speech Services API key
`voiceId`	string	No	Voice ID (e.g., en-US-JennyNeural, en-US-GuyNeural)
`region`	string	No	Azure region (e.g., eastus, westus, westeurope)
`outputFormat`	string	No	Output audio format
`rate`	string	No	Speaking rate (e.g., +10%, -20%, 1.5)
`pitch`	string	No	Voice pitch (e.g., +5Hz, -2st, low)
`style`	string	No	Speaking style (e.g., cheerful, sad, angry - neural voices only)
`styleDegree`	number	No	Style intensity (0.01 to 2.0)
`role`	string	No	Role (e.g., Girl, Boy, YoungAdultFemale)

Output

Parameter	Type	Description
`audioUrl`	string	URL to the generated audio file
`audioFile`	file	Generated audio file object
`duration`	number	Audio duration in seconds
`characterCount`	number	Number of characters processed
`format`	string	Audio format
`provider`	string	TTS provider used

`tts_playht`

Convert text to speech using PlayHT (voice cloning)

Input

Parameter	Type	Required	Description
`text`	string	Yes	The text to convert to speech
`apiKey`	string	Yes	PlayHT API key (AUTHORIZATION header)
`userId`	string	Yes	PlayHT user ID (X-USER-ID header)
`voice`	string	No	Voice ID or manifest URL
`quality`	string	No	Quality level (draft, standard, premium)
`outputFormat`	string	No	Output format (mp3, wav, ogg, flac, mulaw)
`speed`	number	No	Speed multiplier (0.5 to 2.0)
`temperature`	number	No	Creativity/randomness (0.0 to 2.0)
`voiceGuidance`	number	No	Voice stability (1.0 to 6.0)
`textGuidance`	number	No	Text adherence (1.0 to 6.0)
`sampleRate`	number	No	Sample rate (8000, 16000, 22050, 24000, 44100, 48000)

Output

Parameter	Type	Description
`audioUrl`	string	URL to the generated audio file
`audioFile`	file	Generated audio file object
`duration`	number	Audio duration in seconds
`characterCount`	number	Number of characters processed
`format`	string	Audio format
`provider`	string	TTS provider used

Notes

Category: tools
Type: tts

Text-to-Speech

On this page