Text to Speech for Podcast and Audio Content Production
Turn scripts, articles, and show notes into broadcast-quality MP3 in one API call. 43 voices, long-form support, €8/1M chars.
Re-recording a script change costs an hour in the studio
With TTS narration, fixing a single sentence is a one-line text edit and one API call — the new audio renders in seconds. No re-scheduling, no editor retakes, no re-upload.
Long-form text needs a stable voice across the whole episode
Audexum's voices are model-weights, not style-transfer on a seed clip. The F1 voice on paragraph 1 is acoustically identical to F1 on paragraph 200. There is no voice drift across long episodes.
Multilingual editions are expensive to produce manually
With 33 languages on the same endpoint, you can generate a Spanish, French, and German edition of the same episode by changing the lang parameter. Cost scales linearly with character count — not with the number of languages.
Article-to-audio conversion is already built
The free Article-to-Audio tool on this site converts any URL or pasted text to a downloadable MP3 using your account's voice settings. It handles chapter breaks, title injection, and attribution — no code required.
First audio in 60 seconds.
No SDK — one POST request, binary audio in the response body.
import requests, pathlib
API = "https://audexum.com/api/synthesize"
KEY = "sk_..." # or os.environ["AUDEXUM_API_KEY"]
def generate_episode(script: str, voice: str = "F1", lang: str = "en") -> bytes:
"""Return MP3 bytes for a full episode script."""
r = requests.post(
API,
headers={"Authorization": f"Bearer {KEY}"},
json={"text": script, "voice": voice, "lang": lang, "format": "mp3"},
timeout=120,
)
r.raise_for_status()
return r.content
# Generate English + Spanish editions from the same script
script_en = pathlib.Path("episode_42_en.txt").read_text()
script_es = pathlib.Path("episode_42_es.txt").read_text()
pathlib.Path("ep42_en.mp3").write_bytes(generate_episode(script_en, lang="en"))
pathlib.Path("ep42_es.mp3").write_bytes(generate_episode(script_es, lang="es"))
print("Done — two editions rendered.")Full parameter reference: audexum.com/docs. Supported formats: wav, mp3, ogg. Supported voices: F1–F5, M1–M5 (43 voices total). Supported languages: 33.
Transparent, no per-use-case surcharge.
Every plan covers every use case at the same character rate. PAYG credits never expire.
All plans include STT (speech-to-text dictation) at no extra cost. Full pricing details →
Tools and guides for this use case.
What is the maximum text length per request?+
Single requests support up to 10,000 characters. For longer episodes, split at sentence or paragraph boundaries and concatenate the returned MP3/WAV files. The Audiobooks page in your dashboard handles this splitting automatically for .txt, .epub, and .pdf files.
Which voice sounds best for narration?+
For English narration, F1 (warm, measured cadence) and M2 (authoritative baritone) are most commonly used for podcast-style content. Try them without creating an account at audexum.com/try.
Can I generate in 33 languages without extra cost?+
Yes. Every plan tier prices all 33 languages identically. A Spanish episode costs the same character count as an English episode. No language surcharge.
Does Audexum have a no-code option for podcasters who don't want to use an API?+
Yes — the Article-to-Audio tool at /tools/article-to-audio and the Audiobooks app at /audiobooks both operate without writing any code. Paste a URL or upload a file; download the MP3.
Same API, every use case.
One endpoint handles Discord bots, podcast narration, e-learning courses, accessibility audio, and newsletter editions.
Start free. Ship fast.
10,000 characters per month, no credit card required. First audio in your terminal in 60 seconds.
Questions? [email protected]