API Documentation for Podcast Audio Generation

By PodcastVoice API editorial team · Updated 2026-11-18

Welcome to the PodcastVoice API documentation, designed specifically for freelance podcasters and audio creators. This guide provides everything you need to turn your scripts into broadcast-ready audio files using a simple, transparent REST API. Whether you are building a custom podcast workflow or automating voiceovers for multiple episodes, you will find clear examples and precise technical details to get started quickly.

We cover authentication, endpoint usage, and integration with popular tools like Python and JavaScript. You will learn how to manage your API key, select from eight high-quality multilingual voices, and handle rate limits effectively. All examples use the standard OpenAI-compatible format, so you can leverage existing SDKs with minimal configuration. Let’s get your content spoken.

API Documentation for Podcast Audio Generation

Frequently asked questions

What is the API endpoint?

Send a POST request to https://api.get28s.com/v1/audio/speech with a JSON body containing your text and voice parameters. This endpoint generates the audio file and returns it directly in the response, allowing you to integrate TTS into your podcast production workflow.

How do I authenticate?

Include your API key in the request header as Authorization: Bearer tts-.... Each account has one active key; you can issue a new key at any time, which immediately invalidates the old one, ensuring secure access to your generation credits.

What models are available?

The API offers two models: "tts-1" and "tts-1-hd". Both use the same engine and pricing structure, allowing you to choose based on your quality preferences without any difference in cost or voice capabilities for your podcast episodes.

What voices can I use?

You can choose from eight presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. These voices cover various tones from warm narration to energetic promos, all based on licensed recordings.

What languages are supported?

We support 23 languages including English, Spanish, German, French, Japanese, and Arabic. Any voice can speak any supported language. If you do not set the language, it is guessed from the script, defaulting to English for Latin text.

How do I change the speed?

Adjust the speed parameter in your request, which accepts values between 0.25 and 4.0. This allows you to fine-tune the pacing of your voiceovers, making them faster for quick updates or slower for detailed explanations in your podcasts.

What formats are supported?

You can receive audio in mp3, wav, opus, flac, or pcm formats. Choose the format that fits your editing software and distribution platform.

What are the rate limits?

You are limited to 60 requests per minute per key, or 10 per minute before your first top-up. Requests are processed sequentially, so under heavy load, a request may wait in a queue before synthesis begins.

How do I handle errors?

If synthesis fails, the charge is returned in full, so you are not billed for unsuccessful attempts. Check your response status and retry if necessary, ensuring your podcast production workflow remains cost-effective and predictable without unexpected charges.

Can I use the OpenAI SDK?

Yes, the official OpenAI SDKs work by changing the base_url to https://api.get28s.com/v1 and using your site-specific key. This allows you to leverage familiar tools and code structures while accessing our multilingual voice generation capabilities.

How do I split long texts?

Split your input text into parts of up to 4096 characters per request. Generate audio for each part separately, then join the resulting audio files. This ensures optimal processing and avoids exceeding the character limit for a single synthesis job.

Is the API compatible with OpenAI?

The request shape matches the OpenAI speech endpoint, making it compatible with OpenAI SDKs when you adjust the base URL. However, we are not affiliated with OpenAI.

How do I get my API key?

Sign up on the /get-api-key/ page using Google or an email and password. Once registered, your dashboard displays your API key, balance, and usage, giving you immediate access to start generating voiceovers for your podcast projects.

What is the base URL?

The API base URL is https://api.get28s.com/v1. Use this for all requests, including the speech endpoint and other endpoints like /voices and /models, ensuring consistent access to all features of the PodcastVoice API for your integration.

First request

curl

curl https://api.get28s.com/v1/audio/speech \
  -H "Authorization: Bearer $TTS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
  --output hello.mp3

Python (openai)

from openai import OpenAI

client = OpenAI(base_url="https://api.get28s.com/v1", api_key="tts-...")

with client.audio.speech.with_streaming_response.create(
    model="tts-1", voice="nova", input="Hello from Python.", response_format="mp3"
) as response:
    response.stream_to_file("hello.mp3")

Node.js (openai)

import OpenAI from "openai";
import fs from "node:fs";

const client = new OpenAI({ baseURL: "https://api.get28s.com/v1", apiKey: process.env.TTS_API_KEY });
const res = await client.audio.speech.create({ model: "tts-1", voice: "milo", input: "Hello from Node.js." });
fs.writeFileSync("hello.mp3", Buffer.from(await res.arrayBuffer()));
voice
ariafemale
novafemale
lunafemale
sagefemale
felixmale
milomale
atlasmale
orionmale
language
arالعربية
zh中文
daDansk
nlNederlands
enEnglish
fiSuomi
frFrançais
deDeutsch
elΕλληνικά
heעברית
hiहिन्दी
itItaliano
ja日本語
ko한국어
msBahasa Melayu
noNorsk
plPolski
ptPortuguês
ruРусский
esEspañol
swKiswahili
svSvenska
trTürkçe

Authentication

Sound wave illustration for: Authentication

Your API key authenticates every request to the PodcastVoice API. You receive one active key per account, which appears on your dashboard after signing up via Google or email. This key grants access to speech generation, voice listings, and usage metrics.

API Key Usage

API Key Usage

Include your key in the HTTP header as a Bearer token. Use the format Authorization: Bearer tts-.... Each request consumes characters from your balance, so keep your key secure but accessible to your automation scripts.

  • Keys start with 'tts-' followed by alphanumeric characters.
  • One active key per account; issuing a new one invalidates the old immediately.

Bearer Token

Bearer Token

The Bearer token ensures that only your account’s credits are charged. Pass it in every POST request to /v1/audio/speech and GET requests to /v1/voices or /v1/models. If the token is missing or invalid, the API returns a 401 error.

Key Management

You can regenerate your API key at any time from the dashboard. The old key stops working instantly, preventing unauthorized use if compromised. Since each account holds only one key, regeneration is a simple security step rather than a complex rotation process.

Endpoints Overview

Sound wave illustration for: Endpoints Overview

Our API exposes three core endpoints to power your podcast production pipeline. You generate audio, manage voice assets, and verify model details through simple HTTP requests.

Each endpoint is designed for clarity and speed, allowing you to integrate speech synthesis into your existing content workflows with minimal friction.

Speech Generation

The primary endpoint accepts your script and returns broadcast-ready audio. Send a POST request to /v1/audio/speech with your text, voice, and format preferences.

The service processes requests sequentially, so longer texts may require splitting. Failed synthesis returns zero charges, ensuring you only pay for successful outputs.

  • Endpoint: POST /v1/audio/speech
  • Accepts JSON body with input, voice, and response_format
  • Returns audio file directly in response

List Voices

Retrieve the full list of available voices, languages, and supported formats via GET /v1/voices. This helps you match the right tone to your podcast segment.

You can filter by language or voice type to find the perfect narrator for your content, from warm narrators to energetic promo voices.

  • Endpoint: GET /v1/voices
  • Returns voice presets and metadata
  • Includes language and format support details

Model Information

Check available models with GET /v1/models. Both tts-1 and tts-1-hd use the same engine and pricing, giving you flexibility without cost surprises.

Use this endpoint to verify model status and ensure your integration is using the latest stable configurations.

  • Endpoint: GET /v1/models
  • Returns tts-1 and tts-1-hd
  • Same engine and price for both

Request Parameters

Sound wave illustration for: Request Parameters

To generate broadcast-ready audio, your request body must include the text to synthesize, a chosen voice preset, and the desired audio format. The API processes these inputs to return a clean audio file ready for your podcast edit.

Text Input

Provide your script in the input field. You can send up to 4096 characters per request. Spaces and punctuation count toward this limit.

  • Maximum 4096 characters per request
  • Spaces and punctuation count as characters
  • Longer texts should be split into multiple requests

Voice Selection

Choose from 8 presets like aria for warm narration or atlas for neutral news delivery. Every voice supports all 23 languages. Set the language parameter if the text uses Latin script but is not English.

  • 8 distinct voice presets available
  • Supports all 23 listed languages
  • Default language is English for Latin script

Speed Control

Adjust the speed parameter between 0.25 and 4.0 to match your pacing needs. Standard speed is 1.0. Faster speeds reduce generation time but may affect clarity.

  • Range: 0.25 to 4.0
  • Standard speed is 1.0
  • Adjust to match podcast pacing

Response Formats

Sound wave illustration for: Response Formats

The API returns synthesized audio directly in the response body, allowing you to save or stream the file immediately. You can choose from multiple formats to suit your podcast production workflow, balancing file size and quality based on your distribution needs.

MP3 Output

MP3 is the default format and ideal for web delivery and most podcast platforms. It offers a good balance between audio quality and small file size, making it easy to store and distribute your episodes.

WAV Output

WAV provides uncompressed audio suitable for editing in professional DAWs. Use this format if you need to apply effects, fade-ins, or mix the voiceover with music and sound effects.

Other Formats

We also support Opus, FLAC, and PCM. Opus is great for efficient data transfer, FLAC for lossless archival, and PCM for raw data processing. Select the format that best fits your specific technical requirements.

Rate Limits

Sound wave illustration for: Rate Limits

Every API key is limited to 60 requests per minute. If you are just starting out, this limit drops to 10 requests per minute until your first top-up is processed. This ensures fair usage while you build your podcast episodes.

60 Requests Per Minute

Once your account is funded, you can process up to 60 synthesis requests in a single minute. This is sufficient for most freelance podcasters generating individual segments or short intros without hitting a bottleneck.

Queue Processing

Requests are processed sequentially, meaning under heavy load, your request may wait in a queue. Long texts are split into 4096-character parts, which are joined after generation. Expect typical speeds of roughly 25 characters per second.

Retry Logic

If a request fails due to a temporary issue, the charge is fully refunded. Implement exponential backoff in your integration to handle transient errors gracefully. Always check the response status to confirm successful audio generation before proceeding.

  • Use exponential backoff for retries
  • Check status codes for success/failure
  • Failed requests are free
Rate Limits

Error Handling

Sound wave illustration for: Error Handling

API errors are straightforward. If synthesis fails, the request is free. You only pay for successful generations, so you can retry safely without worrying about double-charging your balance.

Common Errors

Most errors are simple: invalid API keys, exceeded rate limits, or malformed JSON. The API returns standard HTTP status codes (400, 401, 429, 500) with a clear message. Check your request body for missing fields like input or voice.

  • 400 Bad Request: Invalid parameters or missing text.
  • 401 Unauthorized: Wrong or expired API key.
  • 429 Too Many Requests: You hit the 60 req/min limit.
  • 500 Server Error: Temporary synthesis failure.

Retry Strategy

For 429 errors, wait a few seconds before retrying. For 500 errors, a simple exponential backoff works well. Since requests are processed sequentially, brief waits help avoid queue congestion. Always check the response body for specific error details.

Cost Recovery

If a synthesis fails, the charge is returned in full. Failed requests are free, so you can retry the same text multiple times without extra cost. This makes testing voice styles and speeds very affordable during development.

Integration Examples

Sound wave illustration for: Integration Examples

Jump straight into your podcast workflow with these ready-to-use integration snippets. Whether you are scripting automation in Python or handling web-based generation in JavaScript, the OpenAI SDKs adapt seamlessly to our API base.

These examples demonstrate the core request structure for generating broadcast-ready audio files, allowing you to focus on content creation rather than infrastructure setup.

Curl Command

Use this command to generate a 5-second English clip immediately. Replace YOUR_API_KEY with your token from the dashboard.

curl -X POST "https://api.get28s.com/v1/audio/speech" \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "tts-1", "input": "Hello from your new podcast", "voice": "aria", "response_format": "mp3"}'

  • Ensure your key starts with "tts-".
  • Use mp3 for standard podcast episodes.
  • Adjust speed between 0.25 and 4.0.

Python SDK

Install the official OpenAI package and point it to our endpoint. This approach handles JSON parsing automatically.

import openai client = openai.OpenAI(base_url="https://api.get28s.com/v1", api_key="YOUR_API_KEY") speech_file = client.audio.speech.create( model="tts-1", voice="nova", input="This is a test of the Python SDK." )

  • Set base_url to our API domain.
  • Use model "tts-1" or "tts-1-hd".
  • Voice presets like nova or atlas work directly.

JavaScript SDK

For web-based podcast tools, initialize the client with our base URL. This allows you to generate audio directly in the browser or Node.js environment.

const openai = new OpenAI({ apiKey: "YOUR_API_KEY", baseURL: "https://api.get28s.com/v1" }); const audio = await openai.audio.speech.create({ model: "tts-1", voice: "sage", input: "Hello listeners, welcome to the show." });

  • Configure baseURL for correct routing.
  • Pass voice presets as strings.
  • Handle the response as a blob.

Best Practices for Podcasters

Sound wave illustration for: Best Practices for Podcasters

Podcasters often have scripts longer than the 4,000-character limit per request. The API handles this naturally, but you must manage the segmentation yourself to ensure clean transitions between segments.

Text Splitting

Split your script into chunks of up to 4096 characters. This ensures each API call stays within limits and avoids truncation. Count spaces and punctuation, as they count toward the character limit.

Audio Joining

Concatenate the resulting audio files to create an episode. Use a simple audio library or command-line tool to stitch the MP3 or WAV files together in the order you sent them. This maintains the narrative flow without gaps.

Latency Optimization

Generation takes roughly real-time speed (25 characters per second). For long episodes, plan for queue delays since requests are processed sequentially. Pre-generate your content during off-peak hours to avoid waiting for synthesis during live broadcasts.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. The price difference is non-existent, making the choice purely about aesthetic preference.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. W3C WAI: making audio and video accessible
  3. Tether (USDT)
  4. openai-python on GitHub
  5. Node.js documentation
  6. TRON developer hub: TRC-20
  7. LibriTTS-R paper (arXiv 2305.18802)
  8. LibriVox public-domain audiobooks
  9. OpenAI API reference: create speech
  10. Python documentation
  11. openai-node on GitHub
  12. LibriTTS-R corpus (OpenSLR 141)

More on this site