Name: voice
Price: 0.05 USDC
Availability: InStock

$ man voice

agentutility / synthforge / voice

PRICE / CALL

$0.05

USDC · base mainnet · scheme: exact

METHOD

POST

CLUSTER

synthforge

CATEGORY

STATUS

● live

NAME

voice — create a hosted audio url for a recurring narration, ivr prompt, or accessibility read-aloud

SYNOPSIS

POST https://x402.agentutility.ai/voice
     Content-Type: application/json
     X-PAYMENT:    <signed-transferWithAuthorization>

     { ... }

↳ first call → 402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.

DESCRIPTION

Create a hosted audio URL for a recurring narration, IVR prompt, or accessibility read-aloud. Send up to 4,000 characters with a voice, model, speed, and mp3, wav, opus, aac, or flac format; receive audio_url, file size, content type, and the settings used. Save the selected voice settings with the script so the next revision keeps the same narrator. The finished file is hosted on fal.ai storage. Use it as a text-to-speech API, repeatable narration API, script-to-audio service, or accessibility read-aloud.

INPUT — request schema

property	type	description	req?
text	string	Text to synthesize into speech. Max 4000 chars.	required
voice	string	Voice id, e.g. 'af_sky'. Optional, default 'af_sky'.	optional
model	string	TTS model id. Optional, default 'tts-kokoro'.	optional
speed	number	Playback speed multiplier. Optional, 0.25-4, default 1.	optional
format	string	Output audio format: mp3, wav, opus, aac, or flac. Optional, default mp3. enum: mp3 · wav · opus · aac · flac	optional

OUTPUT — response shape

field	type	description
audio_url	string	Signed URL to the generated audio file hosted on R2 or similar object storage.
file_size_bytes	number	Size of the generated audio file in bytes.
content_type	string	MIME type of the audio response, like audio/mpeg or audio/wav.
format	string	Audio container/codec returned: mp3, wav, opus, aac, or flac.
voice	string	Voice ID used for synthesis, like af_sky.
model	string	TTS model that produced the audio: Kokoro, xAI, ElevenLabs, Orpheus, or MiniMax.
speed	number	Playback speed multiplier applied during synthesis, where 1.0 is normal pace.
input_chars	number	Number of characters in the input text that were synthesized.

EXAMPLES — two ways to call

EXAMPLE 1 · curl

curl -X POST https://x402.agentutility.ai/voice \
  -H 'Content-Type: application/json' \
  -d '{ }'

first response = 402 Payment Required with payment requirements; sign + retry with X-PAYMENT.

EXAMPLE 2 · mcp

# Install the MCP package for this endpoint's cluster
npx -y @agentutility/mcp-<cluster>

# Required: EVM private key with USDC on Base
export X402_PRIVATE_KEY=0x...

# Then call the voice tool from your MCP-aware agent.

MCP server handles payment automatically — your coding agent just calls the tool by name.

METADATA

tags: ttsspeechaudiovoiceai
env: VENICE_API_KEY · FAL_KEY
methods: POST
cluster: synthforge
price: $0.05 USDC per call

ADJACENT — other endpoints in synthforge

endpoint	description	price
text-to-speech	Generate a hosted audio URL each time an updated script needs the same narrator.	$0.05
image-generate-pro	Premium text-to-image API for repeatable product, campaign, and design assets when a standard draft needs a selected model tier.	$0.06
recraft	Generates SFW design and illustration images with Venice's recraft-v4 model on a dedicated endpoint.	$0.06
seedream	Generates SFW images with Venice's seedream-v4 model on a dedicated endpoint.	$0.06
flux-2-pro	Generates SFW images with Venice's flux-2-pro model on a dedicated endpoint.	$0.04
qwen-image	Generates SFW images with Venice's qwen-image model on a dedicated endpoint.	$0.04
background-remove	Removes the background from a public image URL and returns the subject with alpha transparency.	$0.08
background-remover	Removes the background from product, portrait, and object images, returning alpha PNG foreground cutouts with optional crop-to-bounding-b…	$0.08