return male_audio male_audio = gtts_male_voice("This is a male-sounding voice using GTTS.") male_audio.export("male_voice.mp3", format="mp3")
import pyttsx3 engine = pyttsx3.init() voices = engine.getProperty('voices') for v in voices: print(v.id, v.name, v.gender) # Some show gender Pick a male voice (e.g., 'HKEY_LOCAL_MACHINE\SOFTWARE...' on Windows) for v in voices: if 'male' in v.name.lower(): engine.setProperty('voice', v.id) break
from google.cloud import texttospeech client = texttospeech.TextToSpeechClient() synthesis_input = texttospeech.SynthesisInput(text="Hello, I am a male voice") voice = texttospeech.VoiceSelectionParams( language_code="en-US", name="en-US-Neural2-D", # Male voice ssml_gender=texttospeech.SsmlVoiceGender.MALE ) audio_config = texttospeech.AudioConfig(audio_encoding=texttospeech.AudioEncoding.MP3) response = client.synthesize_speech(input=synthesis_input, voice=voice, audio_config=audio_config) gtts male voice
engine.say("Hello, I am a male voice using pyttsx3") engine.runAndWait()
Here’s a useful, practical guide to using — covering how to get it, why it matters, and workarounds since GTTS itself doesn’t natively support male/female selection. 1. The Core Fact: GTTS Has No Explicit Male/Female Parameter The gtts library (Google Text-to-Speech) uses Google’s standard TTS API, which provides one voice per language — and that voice is typically female-sounding for most languages (e.g., English, Spanish, French). You cannot directly call gtts with voice='male' . You cannot directly call gtts with voice='male'
# Load audio audio = AudioSegment.from_file(fp, format="mp3")
from gtts import gTTS tts = gTTS(text="Hello", lang="en") # always the default voice (female) The only reliable way is to switch to a different TTS engine or post-process the audio (pitch shifting). Here’s a clean Python approach using pydub to lower the pitch of the GTTS output, making it sound more masculine. Step-by-step male voice transformation: from gtts import gTTS from pydub import AudioSegment from pydub.effects import speedup import io def gtts_male_voice(text, lang='en', pitch_semi= -3): # Generate normal GTTS audio tts = gTTS(text, lang=lang) fp = io.BytesIO() tts.write_to_fp(fp) fp.seek(0) Better Alternative: Use pyttsx3 (Offline
This is a timbre shift, not a true male voice model. It sounds deeper but may be slightly robotic. 3. Better Alternative: Use pyttsx3 (Offline, Male Voice Selectable) If you need real male voices without cloud dependency, use pyttsx3 (works on Windows, macOS, Linux).