Docs Navigation

Blocks

Text to Speech

Convert text to speech using multiple providers

Converts text to natural-sounding speech using various TTS providers including OpenAI, ElevenLabs, Google, and Deepgram.

Back to Catalog

Toolstext_to_speech

Block Preview

Text to Speech

Convert text to speech using multiple providers

Usage

Add the block to your workflow and connect it to the upstream step.
Configure any required credentials or tokens in the inputs.
Fill in required inputs and optional parameters for the run.
Run a test execution, inspect outputs, and iterate before deploying.
Deploy the text_to_speech block with monitoring enabled in production.

Inputs (UI)

Provider

dropdown

Layout: half

Options: OpenAI TTS, ElevenLabs, Google TTS, Deepgram

Text

long-input

Placeholder: Text to convert to speech...

Layout: full

Voice

dropdown

Layout: half

Condition: provider = "openai"

Options: Alloy, Echo, Fable, Onyx

Voice ID

short-input

Placeholder: Enter ElevenLabs voice ID

Layout: half

Condition: provider = "elevenlabs"

Model

dropdown

Layout: half

Condition: provider = "openai"

Options: TTS-1, TTS-1 HD

Model

dropdown

Layout: half

Condition: provider = "elevenlabs"

Options: Eleven Multilingual v2, Eleven Turbo v2, Eleven Monolingual v1

Speed

slider

Layout: half

Condition: provider = "openai"

Stability

slider

Layout: half

Condition: provider = "elevenlabs"

Similarity Boost

slider

Layout: half

Condition: provider = "elevenlabs"

Output Format

dropdown

Layout: half

Options: MP3, WAV, OGG, FLAC

Return Base64

switch

Return audio as base64 instead of URL

Layout: half

API Key

short-input

Placeholder: API key or $ENV_VAR

Layout: full

Inputs (API)

provider

string

Optional

text

string

Required

voice

string

Optional

model

string

Optional

speed

number

Optional

stability

number

Optional

similarity

number

Optional

outputFormat

string

Optional

returnBase64

boolean

Optional

apiKey

string

Optional

Outputs

Primary response type:

{
  "audioUrl": "string",
  "audioData": "string",
  "format": "string",
  "duration": "number",
  "characterCount": "number",
  "voice": "string",
  "provider": "string"
}

Tool Access

text_to_speech