How do I generate MP3 speech from text in Python?

To generate MP3 speech from text in Python, the simplest options are:

1) Use Google Text-to-Speech (gTTS) — easy and free for basic use

Install

pip install gTTS

Example

from gtts import gTTS

text = "Hello, this is a text to speech example in Python."
tts = gTTS(text=text, lang="en")

tts.save("speech.mp3")
print("Saved speech.mp3")

Notes

• Produces an MP3 file directly.
• Requires internet access.
• Good for small projects or prototypes.

---

2) Use pyttsx3 — offline, but outputs WAV more naturally

pyttsx3 works offline, but it usually saves to WAV or plays audio rather than creating MP3 directly. If you need MP3, you’d typically convert the WAV to MP3 afterward.

Install

pip install pyttsx3 pydub

You’ll also need ffmpeg installed for conversion.

Example

import pyttsx3
from pydub import AudioSegment

text = "Hello, this is offline speech generation."

engine = pyttsx3.init()
engine.save_to_file(text, "speech.wav")
engine.runAndWait()

audio = AudioSegment.from_wav("speech.wav")
audio.export("speech.mp3", format="mp3")
print("Saved speech.mp3")

---

3) Use cloud TTS services for higher quality voices

If you want more natural voices and control, use:

• Google Cloud Text-to-Speech
• Amazon Polly
• Microsoft Azure Speech

These typically require an API key and billing setup, but they can generate MP3 directly.

---

Recommended approach

• Quick and easy: gTTS
• Offline: pyttsx3 + ffmpeg
• Best quality: cloud TTS APIs

If you want, I can show you:

1. a version that reads text from a file,
2. a Flask/FastAPI endpoint that returns MP3, or
3. a script using AWS/Google/Azure TTS.