apyhub
Back
▣ OUTPUT KIT

Convert Text to Speech API

Hosted on ApyHub

What it does

The Text to Speech API turns written content into MP3 audio. Send up to 75,000 characters of text in a JSON body, upload a document as a file, or pass a document url, and choose a male or female voice with gender. The /file endpoints return the MP3 directly, and the /link endpoints return a JSON data field with a signed URL.

Because it accepts documents as well as text, it also works as a PDF to audio API: send a PDF and get it read aloud as an MP3, with no text extraction step on your side. Teams use the text to speech API to add read-aloud buttons to articles, narrate reports and training material, make content accessible to people who prefer listening, and send voice notifications from apps. It works from Python, Node.js or any language that can send an HTTP request.

There are two voices, male and female. For many voices, voice cloning or fine pronunciation control, a dedicated speech platform is a better fit.

To go the other way, use the Speech to Text API. To shorten long documents before narrating them, use the AI Summarize API. AI agents can also call it through ApyHub MCP, for example to turn a summary into an MP3.

▣ ENDPOINT 01 / 06
POST
Convert uploaded document to MP3
https://api.eu.apyhub.com/apyhub/convert-text-to-speech/file/file

QUICKSTART

GUIDE

Quickstart

Upload a text file and choose a voice gender to generate speech.

curl -X POST "https://api.eu.apyhub.com/apyhub/convert-text-to-speech/file/file" \
  -H "apy-token: $APY_TOKEN" \
  -F "file=@/path/to/input.txt" \
  -F "gender=male"

What you'll get back

Returns a binary file response containing the generated audio.

TRY ITLIVE · 750 ATOMS
Loading your default key…
The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.
Max 100MB total per request (all files combined). Larger? Use this API's URL-based endpoint instead, if it has one.
body*

About this endpoint

What it does

Uploads a document file and a selected voice gender, then returns the generated MP3 audio as binary data.

Request Body

ParameterTypeDescription
fileBinaryBinary file upload containing the document to process.
genderENUMVoice gender to use for the audio output. Allowed values: male, female.

Response

Returns a binary file response containing the generated MP3 audio.

ParameterTypeDescription
binaryStringThe MP3 audio file returned by the endpoint as binary data.

Max 100MB total per request (all files combined). Larger? Use this API's URL-based endpoint instead, if it has one.

▣ ENDPOINT 02 / 06
POST
Convert uploaded document to signed MP3 link
https://api.eu.apyhub.com/apyhub/convert-text-to-speech/file/link

QUICKSTART

GUIDE

Quickstart

Convert a file to speech by uploading the file and choosing a voice gender.

curl -X POST "https://api.eu.apyhub.com/apyhub/convert-text-to-speech/file/link" \
  -H "apy-token: $APY_TOKEN" \
  -F "file=@/path/to/audio-or-text-file" \
  -F "gender=male"

What you'll get back

Returns a JSON object with a data string field.

{
  "data": "https://example.com/generated-audio.mp3"
}
TRY ITLIVE · 750 ATOMS
Loading your default key…
The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.
Max 100MB total per request (all files combined). Larger? Use this API's URL-based endpoint instead, if it has one.
body*

About this endpoint

What it does

Converts the text content from an uploaded document into speech and returns a signed MP3 link. The request body includes the uploaded file and the voice gender to use.

Request Body

ParameterTypeDescription
fileBinaryUploaded document file in binary format.
genderENUMVoice gender to use. Allowed values: male, female.

Response

Returns a JSON object with a data string field containing the signed MP3 link.

ParameterTypeDescription
dataStringSigned MP3 link.

Max 100MB total per request (all files combined). Larger? Use this API's URL-based endpoint instead, if it has one.

▣ ENDPOINT 03 / 06
POST
Convert JSON text to MP3 download
https://api.eu.apyhub.com/apyhub/convert-text-to-speech/text/file

QUICKSTART

GUIDE

Quickstart

Send text and a gender to generate speech audio from the supplied text.

curl -X POST "https://api.eu.apyhub.com/apyhub/convert-text-to-speech/text/file" \
  -H "apy-token: $APY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text":"Hello world, this is a sample speech synthesis request.","gender":"female"}'

What you'll get back

Returns binary audio data (string with binary format), not a JSON object.

(binary audio file)
TRY ITLIVE · 750 ATOMS
Loading your default key…
The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.
body*

About this endpoint

What it does

Converts the provided text into an MP3 file download. You send the text and a voice gender selection in the request body, and the endpoint returns the generated audio as binary data.

Request Body

ParameterTypeDescription
textStringText to synthesize. Maximum length: 75000 characters.
genderENUMVoice gender to use. Allowed values: male, female.

Response

Returns a binary file response containing the generated MP3 audio.

ParameterTypeDescription
fileStringBinary audio content for the synthesized MP3 download.
▣ ENDPOINT 04 / 06
POST
Convert JSON text to signed MP3 link
https://api.eu.apyhub.com/apyhub/convert-text-to-speech/text/link

QUICKSTART

GUIDE

Quickstart

Send the text and voice gender to generate a speech synthesis link.

curl -X POST "https://api.eu.apyhub.com/apyhub/convert-text-to-speech/text/link" \
  -H "apy-token: $APY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello world, this is a sample speech synthesis request.",
    "gender": "female"
  }'

What you'll get back

Returns a JSON object with a data string field containing the generated audio link.

{
  "data": "https://..."
}
TRY ITLIVE · 750 ATOMS
Loading your default key…
The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.
body*

About this endpoint

What it does

Converts the submitted JSON text into a speech audio file and returns a signed MP3 link in the response. The request body includes the text to synthesize and the voice gender to use.

Request Body

ParameterTypeDescription
textStringThe text to convert to speech. Maximum length: 75,000 characters.
genderENUMThe voice gender to use. Allowed values: male, female.

Response

Returns a JSON object with a data string field containing the signed MP3 link.

AttributeTypeDescription
dataStringThe signed MP3 link to the generated MP3 file.
▣ ENDPOINT 05 / 06
POST
Convert document URL to MP3
https://api.eu.apyhub.com/apyhub/convert-text-to-speech/url/file

QUICKSTART

GUIDE

Quickstart

Convert a file from a URL into speech by sending the file URL and voice gender.

curl -X POST "https://api.eu.apyhub.com/apyhub/convert-text-to-speech/url/file" \
  -H "apy-token: $APY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://assets.apyhub.com/samples/sample.pdf",
    "gender": "female"
  }'

What you'll get back

Returns a binary file (string with format: binary) containing the generated audio.

(binary audio file)
TRY ITLIVE · 750 ATOMS
Loading your default key…
The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.
body*

About this endpoint

What it does

Converts the text content of a document available at a URL into an MP3 audio file. The request takes the document URL and the speaker gender, and the response is a binary file stream.

Request Body

ParameterTypeDescription
urlStringDocument URL in URI format.
genderENUMAllowed values: male, female.

Response

Returns a binary response containing the generated MP3 audio file. The success response is a single binary payload, not a JSON object.

ParameterTypeDescription
binaryStringMP3 file content returned as a binary stream.
▣ ENDPOINT 06 / 06
POST
Convert document URL to signed MP3 link
https://api.eu.apyhub.com/apyhub/convert-text-to-speech/url/link

QUICKSTART

GUIDE

Quickstart

Convert a file URL to speech by sending the source URL and voice gender.

curl -X POST "https://api.eu.apyhub.com/apyhub/convert-text-to-speech/url/link" \
  -H "apy-token: $APY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://assets.apyhub.com/samples/sample.pdf",
    "gender": "female"
  }'

What you'll get back

Returns a JSON object with a data string field.

{
  "data": "https://..."
}
TRY ITLIVE · 750 ATOMS
Loading your default key…
The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.
body*

About this endpoint

What it does

Extracts text from a document URL and returns a signed MP3 link. You send a document url and a voice gender, and the response returns a JSON object containing the generated link in data.

Request Body

ParameterTypeDescription
urlStringDocument URL to process. Must be a valid URI.
genderENUMVoice gender to use. Allowed values: male, female.

Response

Returns a JSON object with a data string field containing the signed MP3 link. Success response schema: object with one top-level field, data as a string.

ParameterTypeDescription
dataStringSigned MP3 link returned by the endpoint.
▣ COMMON ERRORS

Errors any endpoint can return

400bad_request

Required parameter missing or malformed body.

401unauthorized

API key missing, revoked, or not authorized for this service.

429rate_limited

Your plan's per-second rate exceeded. Retry with exponential backoff.

503upstream_busy

Backend temporarily unavailable. Try again in a few seconds.

Similar APIs

Closest matches in the catalog based on this service.

CALLConvert Speech to Text APIApyHubCALLConvert Speech to Text & Subtitles APICallable LabsCALLConvert Speech to Text with (Whisper Large-v3)MasterA AICALLAI Video Transcriber APIApyHub

From the blog

Reads that touch this API.

PDF to Speech: Turning Documents Into Audio With One API CallSep 7, 2026Text to Speech in Python: 5 Ways (Offline, Free and API)Oct 20, 2026Speech Recognition: Use Cases and SolutionsSep 18, 2026Convert WAV to MP3 API – Streamline Audio Workflows for DevelopersJul 9, 2026