diff --git a/README.md b/README.md index cfd32b8..65efb64 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,7 @@ ## Commands -![Total Commands](https://img.shields.io/badge/Total%20Commands-64-5865F2) +![Total Commands](https://img.shields.io/badge/Total%20Commands-65-5865F2) | Command group | Subcommands | | ------------ | --- | @@ -32,7 +32,7 @@ | melonx | `help`, `transfer`, `mods`, `gamecrash`, `requirements`, `error`, `26` | | miscellaneous | `keanu`, `labubu`, `piracy`, `tryitandsee`, `rickroll`, `dontasktoask`, `support`, `depart`, `docs` `sigma` | | utilities | `translate`, `codepreview`, `dictionary` | -| media | `download`, `mcquote`, `img2gif`, `tweety` | +| media | `download`, `mcquote`, `img2gif`, `tweety`, `tts` | ## Download diff --git a/TODO.md b/TODO.md index 6ce745b..3cf7e08 100644 --- a/TODO.md +++ b/TODO.md @@ -51,7 +51,7 @@ - [ ] add ~~admin abuse~~ command (for games) -- [ ] add [tts](https://developer.puter.com/tutorials/free-unlimited-text-to-speech-api/) command +- [x] add [tts](https://developer.puter.com/tutorials/free-unlimited-text-to-speech-api/) command - [x] update botinfo command diff --git a/cogs/media/__init__.py b/cogs/media/__init__.py index c3acee5..f91057e 100644 --- a/cogs/media/__init__.py +++ b/cogs/media/__init__.py @@ -7,6 +7,7 @@ from .download import download_command from .mcquote import mcquote_command from .img2gif import img2gif_command from .tweety import tweety_command +from .tts import tts_command def _require_group_prefix(context: Context) -> bool: @@ -46,7 +47,7 @@ class Media(commands.GroupCog, name="media"): color=0x7289DA ) embed.set_author(name="Media", icon_url="https://yes.nighty.works/raw/y5SEZ9.webp") - embed.add_field(name="Available", value="download, mcquote, img2gif, tweety", inline=False) + embed.add_field(name="Available", value="download, mcquote, img2gif, tweety, tts", inline=False) await context.send(embed=embed) async def _invoke_hybrid(self, context: Context, name: str, *args, **kwargs): @@ -62,6 +63,9 @@ class Media(commands.GroupCog, name="media"): if name == "tweety": await self.tweety(context) return + if name == "tts": + await self.tts(context, text=kwargs.get('text')) + return await context.send(f"Unknown media command: {name}") @media_group.command(name="download") @@ -80,6 +84,10 @@ class Media(commands.GroupCog, name="media"): async def media_group_tweety(self, context: Context): await self._invoke_hybrid(context, "tweety") + @media_group.command(name="tts") + async def media_group_tts(self, context: Context, *, text: str = None): + await self._invoke_hybrid(context, "tts", text=text) + @commands.check(_require_group_prefix) @commands.hybrid_command( name="download", @@ -112,11 +120,20 @@ class Media(commands.GroupCog, name="media"): async def tweety(self, context): return await tweety_command()(self, context) + @commands.check(_require_group_prefix) + @commands.hybrid_command( + name="tts", + description="Convert text to speech using Google Text-to-Speech.", + ) + async def tts(self, context, text: str = None): + return await tts_command()(context, text=text) + async def setup(bot) -> None: cog = Media(bot) await bot.add_cog(cog) - + bot.logger.info("Loaded extension 'media.download'") bot.logger.info("Loaded extension 'media.mcquote'") bot.logger.info("Loaded extension 'media.img2gif'") bot.logger.info("Loaded extension 'media.tweety'") + bot.logger.info("Loaded extension 'media.tts'") diff --git a/cogs/media/tts.py b/cogs/media/tts.py new file mode 100644 index 0000000..6383e35 --- /dev/null +++ b/cogs/media/tts.py @@ -0,0 +1,169 @@ +import asyncio +import io +import tempfile +from typing import Optional + +import discord +from discord import app_commands +from discord.ext import commands +from gtts import gTTS + + +DEFAULT_LANG = "en" + +def tts_command(): + + async def send_embed( + context: commands.Context, + embed: discord.Embed, + *, + ephemeral: bool = False, + file: Optional[discord.File] = None, + ) -> None: + interaction = getattr(context, "interaction", None) + if interaction is not None: + if interaction.response.is_done(): + if file: + await interaction.followup.send(embed=embed, file=file, ephemeral=ephemeral) + else: + await interaction.followup.send(embed=embed, ephemeral=ephemeral) + else: + if file: + await interaction.response.send_message(embed=embed, file=file, ephemeral=ephemeral) + else: + await interaction.response.send_message(embed=embed, ephemeral=ephemeral) + else: + if file: + await context.send(embed=embed, file=file) + else: + await context.send(embed=embed) + + async def generate_tts_audio(text: str) -> tuple[Optional[bytes], Optional[str]]: + try: + loop = asyncio.get_event_loop() + audio_bytes = await loop.run_in_executor( + None, + lambda: _generate_tts_sync(text) + ) + return audio_bytes, None + except Exception as e: + return None, str(e) + + def _generate_tts_sync(text: str) -> bytes: + tts = gTTS(text=text, lang=DEFAULT_LANG, slow=False) + fp = io.BytesIO() + tts.write_to_fp(fp) + fp.seek(0) + return fp.read() + + @commands.hybrid_command( + name="tts", + description="Convert text to speech using Google Text-to-Speech.", + ) + @app_commands.describe( + text="The text to convert to speech", + ) + async def tts(context: commands.Context, text: Optional[str] = None): + if not text or not text.strip(): + if context.message and context.message.reference and context.message.reference.resolved: + referenced = context.message.reference.resolved + if isinstance(referenced, discord.Message) and referenced.content: + text = referenced.content + if not text or not text.strip(): + embed = ( + discord.Embed( + title="Error", + description="Please provide text to convert or reply to a message containing text.", + color=0xE02B2B, + ).set_author(name="Media", icon_url="https://yes.nighty.works/raw/y5SEZ9.webp") + ) + await send_embed(context, embed, ephemeral=True) + return + + text = text.strip() + if len(text) > 500: + embed = ( + discord.Embed( + title="Error", + description="Text is too long. Please limit to 500 characters.", + color=0xE02B2B, + ).set_author(name="Media", icon_url="https://yes.nighty.works/raw/y5SEZ9.webp") + ) + await send_embed(context, embed, ephemeral=True) + return + + processing_embed = ( + discord.Embed( + title="TTS (Processing)", + description=" Generating speech...", + color=0x7289DA, + ).set_author(name="Media", icon_url="https://yes.nighty.works/raw/y5SEZ9.webp") + ) + + interaction = getattr(context, "interaction", None) + processing_message = None + sent_initial_interaction_response = False + + if interaction is not None: + if interaction.response.is_done(): + processing_message = await interaction.followup.send(embed=processing_embed, ephemeral=True) + else: + await interaction.response.send_message(embed=processing_embed, ephemeral=True) + sent_initial_interaction_response = True + else: + processing_message = await context.send(embed=processing_embed) + + audio_bytes, error = await generate_tts_audio(text) + + if error or not audio_bytes: + embed = ( + discord.Embed( + title="Error", + description=f"Failed to generate speech. {error or 'Unknown error.'}", + color=0xE02B2B, + ).set_author(name="Media", icon_url="https://yes.nighty.works/raw/y5SEZ9.webp") + ) + await send_embed(context, embed, ephemeral=True) + if interaction is not None and sent_initial_interaction_response: + try: + await interaction.delete_original_response() + except Exception: + pass + if processing_message: + try: + await processing_message.delete() + except Exception: + pass + return + + audio_file = discord.File( + io.BytesIO(audio_bytes), + filename="audio.mp3", + ) + + embed = ( + discord.Embed( + title="Text-to-Speech", + description=f"**Input:** {text}", + color=0x7289DA, + ) + .set_author(name="Media", icon_url="https://yes.nighty.works/raw/y5SEZ9.webp") + .set_footer( + text=f"Requested by {context.author.display_name}", + icon_url=getattr(context.author.display_avatar, "url", None), + ) + ) + + if interaction is not None: + await context.channel.send(embed=embed) + await context.channel.send(file=audio_file) + try: + await interaction.delete_original_response() + except: + pass + else: + await processing_message.delete() + await context.channel.send(embed=embed) + await context.channel.send(file=audio_file) + + return tts diff --git a/requirements.txt b/requirements.txt index 3e23e11..5f857c8 100644 --- a/requirements.txt +++ b/requirements.txt @@ -5,4 +5,5 @@ python-dotenv yt-dlp Pillow pillow-heif -pytz \ No newline at end of file +pytz +gTTS \ No newline at end of file