Text-to-speech conversion using OpenAI's TTS API for generating high-quality, natural-sounding audio. Supports 6 voices (alloy, echo, fable, onyx, nova, shimmer), speed control (0.25x-4.0x), HD qualit
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
Text-to-speech conversion using OpenAI's TTS API for generating high-quality, natural-sounding audio from text.
This skill activates when the user:
OPENAI_API_KEYopenaipydub| Voice | Type | Description |
|---|---|---|
| alloy | Neutral | Balanced, versatile |
| echo | Male | Warm, conversational |
| fable | Neutral | Expressive, storytelling |
| onyx | Male | Deep, authoritative |
| nova | Female | Friendly, upbeat |
| shimmer | Female | Clear, professional |
from openai import OpenAI import osclient = OpenAI(api_key=os.getenv('OPENAI_API_KEY'))
response = client.audio.speech.create( model="tts-1", # or "tts-1-hd" for higher quality voice="onyx", # choose from: alloy, echo, fable, onyx, nova, shimmer input="Your text here", speed=1.0 # 0.25 to 4.0 (optional) )
with open("output.mp3", "wb") as f: for chunk in response.iter_bytes(): f.write(chunk)
# Basic python -c " from openai import OpenAI client = OpenAI() response = client.audio.speech.create(model='tts-1', voice='onyx', input='Hello world') open('output.mp3', 'wb').write(response.content) "
from openai import OpenAI from pydub import AudioSegment import tempfile import os import reclient = OpenAI() MAX_CHARS = 4096
def split_text(text): if len(text) <= MAX_CHARS: return [text]
chunks = [] sentences = re.split(r'(?<=[.!?])\s+', text) current = '' for sentence in sentences: if len(current) + len(sentence) + 1 <= MAX_CHARS: current += (' ' if current else '') + sentence else: if current: chunks.append(current) current = sentence if current: chunks.append(current) return chunksdef generate_tts(text, output_path, voice='onyx', model='tts-1'): chunks = split_text(text)
if len(chunks) == 1: response = client.audio.speech.create(model=model, voice=voice, input=text) with open(output_path, 'wb') as f: f.write(response.content) else: segments = [] for chunk in chunks: response = client.audio.speech.create(model=model, voice=voice, input=chunk) with tempfile.NamedTemporaryFile(suffix='.mp3', delete=False) as tmp: tmp.write(response.content) segments.append(AudioSegment.from_mp3(tmp.name)) os.unlink(tmp.name) combined = segments[0] for seg in segments[1:]: combined += seg combined.export(output_path, format='mp3') return output_pathUsage
generate_tts("Your long text here...", "output.mp3", voice="nova")
| Model | Quality | Speed | Cost |
|---|---|---|---|
| tts-1 | Standard | Fast | $0.015/1K chars |
| tts-1-hd | High Definition | Slower | $0.030/1K chars |
Supported formats:
mp3opusaacflacresponse = client.audio.speech.create( model="tts-1", voice="onyx", input="Hello", response_format="opus" # or mp3, aac, flac )
from openai import OpenAI, APIError, RateLimitError import timeclient = OpenAI()
def generate_with_retry(text, voice='onyx', max_retries=3): for attempt in range(max_retries): try: response = client.audio.speech.create( model="tts-1", voice=voice, input=text ) return response.content except RateLimitError: if attempt < max_retries - 1: time.sleep(2 ** attempt) # Exponential backoff continue raise except APIError as e: print(f"API Error: {e}") raise
return None
def article_to_podcast(article_text, output_file): intro = "Welcome to today's article reading." outro = "Thank you for listening."full_text = f"{intro}\n\n{article_text}\n\n{outro}" generate_tts(full_text, output_file, voice='nova', model='tts-1-hd') print(f"Podcast saved to {output_file}")
def batch_tts(texts, output_dir, voice='onyx'): import os os.makedirs(output_dir, exist_ok=True)for i, text in enumerate(texts): output_path = os.path.join(output_dir, f"audio_{i+1}.mp3") generate_tts(text, output_path, voice=voice) print(f"Generated: {output_path}")
No automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.