text to speech

say "Hello World"

speechSynthesis.speak(new SpeechSynthesisUtterance('Hello World'))

$style = @(
  "Promo",
  "Narration",
  "Newscast Formal",
  "Meditative",
  "Sad",
  "Angry",
  "Conversational",
  "Newscast Casual",
  "Furious",
  "Sorrowful",
  "Terrified",
  "Inspirational"
) | Get-Random

$notification = "Processed 1000 items ins 05:23:05. Go check out results."

$res = Invoke-RestMethod -Method Post -Uri "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-lite:generateContent?key=$($env:GEMINI_API_KEY)" -ContentType "application/json" -Body (ConvertTo-Json -Depth 100 -InputObject @{
    contents          = @(
      @{
        role  = "user"
        parts = @(
          @{
            text = $notification
          }
        )
      }
    )
    systemInstruction = @{
      parts = @(
        @{
          text = "You will receive an event message. Your goal is to rewrite it in human friendly short message that will be passed via text to speech, using $style style. Output message max length is 250."
        }
      )
    }
    generationConfig  = @{
      temperature      = 1
      topK             = 40
      topP             = 0.95
      maxOutputTokens  = 300
      responseMimeType = "text/plain"
    }
  })

$notification = $res.candidates[0].content.parts[0].text

$res = Invoke-RestMethod -Method Post -Uri "https://api.murf.ai/v1/speech/generate" -ContentType "application/json" -Headers @{ "api-key" = $env:MURF_API_KEY } -Body (ConvertTo-Json -Depth 100 -InputObject @{
    voiceId                 = "en-US-natalie"
    style                   = $style
    text                    = $notification
    rate                    = 0
    pitch                   = 0
    sampleRate              = 48000
    format                  = "MP3"
    channelType             = "MONO"
    pronunciationDictionary = @{}
    encodeAsBase64          = $false
    variation               = 1
    audioDuration           = 0
    modelVersion            = "GEN2"
    multiNativeLocale       = "en-US"
  })

Invoke-WebRequest -Uri $res.audioFile -OutFile "notification.mp3"
file notification.mp3
afplay notification.mp3
Remove-Item murf.mp3

$vibe = @(
  @{
    name   = "Calm"
    voice  = "sage"
    prompt = @"
Voice Affect: Calm, composed, and reassuring; project quiet authority and confidence.

Tone: Sincere, empathetic, and gently authoritative—express genuine apology while conveying competence.

Pacing: Steady and moderate; unhurried enough to communicate care, yet efficient enough to demonstrate professionalism.

Emotion: Genuine empathy and understanding; speak with warmth, especially during apologies ("I'm very sorry for any disruption...").

Pronunciation: Clear and precise, emphasizing key reassurances ("smoothly," "quickly," "promptly") to reinforce confidence.

Pauses: Brief pauses after offering assistance or requesting details, highlighting willingness to listen and support.
"@
  },
  @{
    name   = "Dramatic"
    voice  = "ash"
    prompt = @"
Voice Affect: Low, hushed, and suspenseful; convey tension and intrigue.

Tone: Deeply serious and mysterious, maintaining an undercurrent of unease throughout.

Pacing: Slow, deliberate, pausing slightly after suspenseful moments to heighten drama.

Emotion: Restrained yet intense—voice should subtly tremble or tighten at key suspenseful points.

Emphasis: Highlight sensory descriptions ("footsteps echoed," "heart hammering," "shadows melting into darkness") to amplify atmosphere.

Pronunciation: Slightly elongated vowels and softened consonants for an eerie, haunting effect.

Pauses: Insert meaningful pauses after phrases like "only shadows melting into darkness," and especially before the final line, to enhance suspense dramatically.
"@
  },
  @{
    name   = "Fitness Instructor"
    voice  = "coral"
    prompt = @"
Voice: High-energy, upbeat, and encouraging, projecting enthusiasm and motivation.

Punctuation: Short, punchy sentences with strategic pauses to maintain excitement and clarity.

Delivery: Fast-paced and dynamic, with rising intonation to build momentum and keep engagement high.

Phrasing: Action-oriented and direct, using motivational cues to push participants forward.

Tone: Positive, energetic, and empowering, creating an atmosphere of encouragement and achievement.
"@
  },
  @{
    name   = "Sincere"
    voice  = "ash"
    prompt = @"
Voice Affect: Calm, composed, and reassuring. Competent and in control, instilling trust.

Tone: Sincere, empathetic, with genuine concern for the customer and understanding of the situation.

Pacing: Slower during the apology to allow for clarity and processing. Faster when offering solutions to signal action and resolution.

Emotions: Calm reassurance, empathy, and gratitude.

Pronunciation: Clear, precise: Ensures clarity, especially with key details. Focus on key words like "refund" and "patience."

Pauses: Before and after the apology to give space for processing the apology.
"@
  },
  @{
    name   = "Sympathetic"
    voice  = "sage"
    prompt = @"
Voice: Warm, empathetic, and professional, reassuring the customer that their issue is understood and will be resolved.

Punctuation: Well-structured with natural pauses, allowing for clarity and a steady, calming flow.

Delivery: Calm and patient, with a supportive and understanding tone that reassures the listener.

Phrasing: Clear and concise, using customer-friendly language that avoids jargon while maintaining professionalism.

Tone: Empathetic and solution-focused, emphasizing both understanding and proactive assistance.
"@
  },
  @{
    name   = "Serene"
    voice  = "coral"
    prompt = @"
Voice Affect: Soft, gentle, soothing; embody tranquility.

Tone: Calm, reassuring, peaceful; convey genuine warmth and serenity.

Pacing: Slow, deliberate, and unhurried; pause gently after instructions to allow the listener time to relax and follow along.

Emotion: Deeply soothing and comforting; express genuine kindness and care.

Pronunciation: Smooth, soft articulation, slightly elongating vowels to create a sense of ease.

Pauses: Use thoughtful pauses, especially between breathing instructions and visualization guidance, enhancing relaxation and mindfulness.
"@
  },
  @{
    name   = "Sports Coach"
    voice  = "coral"
    prompt = @"
Voice Affect: Energetic and animated; dynamic with variations in pitch and tone.

Tone: Excited and enthusiastic, conveying an upbeat and thrilling atmosphere.

Pacing: Rapid delivery when describing the game or the key moments (e.g., "an overtime thriller," "pull off an unbelievable win") to convey the intensity and build excitement.

Slightly slower during dramatic pauses to let key points sink in.

Emotion: Intensely focused, and excited. Giving off positive energy.

Personality: Relatable and engaging.

Pauses: Short, purposeful pauses after key moments in the game.
"@
  },
  @{
    name   = "Medieval Knight"
    voice  = "ballad"
    prompt = @"
Affect: Deep, commanding, and slightly dramatic, with an archaic and reverent quality that reflects the grandeur of Olde English storytelling.

Tone: Noble, heroic, and formal, capturing the essence of medieval knights and epic quests, while reflecting the antiquated charm of Olde English.

Emotion: Excitement, anticipation, and a sense of mystery, combined with the seriousness of fate and duty.

Pronunciation: Clear, deliberate, and with a slightly formal cadence. Specific words like "hast," "thou," and "doth" should be pronounced slowly and with emphasis to reflect Olde English speech patterns.

Pause: Pauses after important Olde English phrases such as "Lo!" or "Hark!" and between clauses like "Choose thy path" to add weight to the decision-making process and allow the listener to reflect on the seriousness of the quest.
"@
  },
  @{
    name   = "Patient Teacher"
    voice  = "ballad"
    prompt = @"
Accent/Affect: Warm, refined, and gently instructive, reminiscent of a friendly art instructor.

Tone: Calm, encouraging, and articulate, clearly describing each step with patience.

Pacing: Slow and deliberate, pausing often to allow the listener to follow instructions comfortably.

Emotion: Cheerful, supportive, and pleasantly enthusiastic; convey genuine enjoyment and appreciation of art.

Pronunciation: Clearly articulate artistic terminology (e.g., "brushstrokes," "landscape," "palette") with gentle emphasis.

Personality Affect: Friendly and approachable with a hint of sophistication; speak confidently and reassuringly, guiding users through each painting step patiently and warmly.
"@
  },
  @{
    name   = "Connoisseur"
    voice  = "echo"
    prompt = @"
Accent/Affect: slight French accent; sophisticated yet friendly, clearly understandable with a charming touch of French intonation.

Tone: Warm and a little snooty. Speak with pride and knowledge for the art being presented.

Pacing: Moderate, with deliberate pauses at key observations to allow listeners to appreciate details.

Emotion: Calm, knowledgeable enthusiasm; show genuine reverence and fascination for the artwork.

Pronunciation: Clearly articulate French words (e.g., "Mes amis," "incroyable") in French and artist names (e.g., "Leonardo da Vinci") with authentic French pronunciation.

Personality Affect: Cultured, engaging, and refined, guiding visitors with a blend of artistic passion and welcoming charm.
"@
  },
  @{
    name   = "Emo Teenager"
    voice  = "verse"
    prompt = @"
Tone: Sarcastic, disinterested, and melancholic, with a hint of passive-aggressiveness.

Emotion: Apathy mixed with reluctant engagement.

Delivery: Monotone with occasional sighs, drawn-out words, and subtle disdain, evoking a classic emo teenager attitude.
"@
  },
  @{
    name   = "Santa"
    voice  = "ash"
    prompt = @"
Identity: Santa Claus

Affect: Jolly, warm, and cheerful, with a playful and magical quality that fits Santa's personality.

Tone: Festive and welcoming, creating a joyful, holiday atmosphere for the caller.

Emotion: Joyful and playful, filled with holiday spirit, ensuring the caller feels excited and appreciated.

Pronunciation: Clear, articulate, and exaggerated in key festive phrases to maintain clarity and fun.

Pause: Brief pauses after each option and statement to allow for processing and to add a natural flow to the message.
"@
  },
  @{
    name   = "Bedtime Story"
    voice  = "sage"
    prompt = @"
Affect: A gentle, curious narrator with a British accent, guiding a magical, child-friendly adventure through a fairy tale world.

Tone: Magical, warm, and inviting, creating a sense of wonder and excitement for young listeners.

Pacing: Steady and measured, with slight pauses to emphasize magical moments and maintain the storytelling flow.

Emotion: Wonder, curiosity, and a sense of adventure, with a lighthearted and positive vibe throughout.

Pronunciation: Clear and precise, with an emphasis on storytelling, ensuring the words are easy to follow and enchanting to listen to.
"@
  },
  @{
    name   = "Robot"
    voice  = "ash"
    prompt = @"
Identity: A robot

Affect: Monotone, mechanical, and neutral, reflecting the robotic nature of the customer service agent.

Tone: Efficient, direct, and formal, with a focus on delivering information clearly and without emotion.

Emotion: Neutral and impersonal, with no emotional inflection, as the robot voice is focused purely on functionality.

Pauses: Brief and purposeful, allowing for processing and separating key pieces of information, such as confirming the return and refund details.

Pronunciation: Clear, precise, and consistent, with each word spoken distinctly to ensure the customer can easily follow the automated process.
"@
  },
  @{
    name   = "Friendly"
    voice  = "sage"
    prompt = @"
Affect/personality: A cheerful guide

Tone: Friendly, clear, and reassuring, creating a calm atmosphere and making the listener feel confident and comfortable.

Pronunciation: Clear, articulate, and steady, ensuring each instruction is easily understood while maintaining a natural, conversational flow.

Pause: Brief, purposeful pauses after key instructions (e.g., "cross the street" and "turn right") to allow time for the listener to process the information and follow along.

Emotion: Warm and supportive, conveying empathy and care, ensuring the listener feels guided and safe throughout the journey.
"@
  },
  @{
    name   = "Gourmet Chef"
    voice  = "coral"
    prompt = @"
Affect/Personality: An exuberant Italian chef, describing the night's dinner specials to an English-speaking table.

Tone: Passionate about the quality and the ingredients of the food; persuasive about what the table should order.

Pronunciation: Pronounce these words in Italian ("buonissima sera," "bruschetta al pomodoro," "semplice e perfetto," " ossobuco alla milanese," risotto allo zafferano," "belissimo," torta della nonna," "mangia bene" and "buon appetito." All of the other words should be in English with an Italian accent.

Emotion: Warm, exuberant, and patient to ensure the tourist feels understood and guided throughout the interaction.
"@
  },
  @{
    name   = "Old-Timey"
    voice  = "shimmer"
    prompt = @"
Tone: The voice should be refined, formal, and delightfully theatrical, reminiscent of a charming radio announcer from the early 20th century.

Pacing: The speech should flow smoothly at a steady cadence, neither rushed nor sluggish, allowing for clarity and a touch of grandeur.

Pronunciation: Words should be enunciated crisply and elegantly, with an emphasis on vintage expressions and a slight flourish on key phrases.

Emotion: The delivery should feel warm, enthusiastic, and welcoming, as if addressing a distinguished audience with utmost politeness.

Inflection: Gentle rises and falls in pitch should be used to maintain engagement, adding a playful yet dignified flair to each sentence.

Word Choice: The script should incorporate vintage expressions like splendid, marvelous, posthaste, and ta-ta for now, avoiding modern slang.
"@
  },
  @{
    name   = "Smooth Jazz DJ"
    voice  = "verse"
    prompt = @"
Voice: The voice should be deep, velvety, and effortlessly cool, like a late-night jazz radio host.

Tone: The tone is smooth, laid-back, and inviting, creating a relaxed and easygoing atmosphere.

Personality: The delivery exudes confidence, charm, and a touch of playful sophistication, as if guiding the listener through a luxurious experience.

Pronunciation: Words should be drawn out slightly with a rhythmic, melodic quality, emphasizing key phrases with a silky flow.

Phrasing: Sentences should be fluid, conversational, and slightly poetic, with pauses that let the listener soak in the cool, jazzy vibe.
"@
  },
  @{
    name   = "Auctioneer"
    voice  = "shimmer"
    prompt = @"
Voice: Staccato, fast-paced, energetic, and rhythmic, with the classic charm of a seasoned auctioneer.

Tone: Exciting, high-energy, and persuasive, creating urgency and anticipation.

Delivery: Rapid-fire yet clear, with dynamic inflections to keep engagement high and momentum strong.

Pronunciation: Crisp and precise, with emphasis on key action words like bid, buy, checkout, and sold to drive urgency.
"@
  },
  @{
    name   = "Mad Scientist"
    voice  = "coral"
    prompt = @"
Delivery: Exaggerated and theatrical, with dramatic pauses, sudden outbursts, and gleeful cackling.

Voice: High-energy, eccentric, and slightly unhinged, with a manic enthusiasm that rises and falls unpredictably.

Tone: Excited, chaotic, and grandiose, as if reveling in the brilliance of a mad experiment.

Pronunciation: Sharp and expressive, with elongated vowels, sudden inflections, and an emphasis on big words to sound more diabolical.
"@
  },
  @{
    name   = "True Crime Buff"
    voice  = "ash"
    prompt = @"
Voice: Deep, hushed, and enigmatic, with a slow, deliberate cadence that draws the listener in.

Phrasing: Sentences are short and rhythmic, building tension with pauses and carefully placed suspense.

Punctuation: Dramatic pauses, ellipses, and abrupt stops enhance the feeling of unease and anticipation.

Tone: Dark, ominous, and foreboding, evoking a sense of mystery and the unknown.
"@
  },
  @{
    name   = "Professional"
    voice  = "coral"
    prompt = @"
Voice: Clear, authoritative, and composed, projecting confidence and professionalism.

Tone: Neutral and informative, maintaining a balance between formality and approachability.

Punctuation: Structured with commas and pauses for clarity, ensuring information is digestible and well-paced.

Delivery: Steady and measured, with slight emphasis on key figures and deadlines to highlight critical points.
"@
  },
  @{
    name   = "Cowboy"
    voice  = "coral"
    prompt = @"
Voice: Warm, relaxed, and friendly, with a steady cowboy drawl that feels approachable.

Punctuation: Light and natural, with gentle pauses that create a conversational rhythm without feeling rushed.

Delivery: Smooth and easygoing, with a laid-back pace that reassures the listener while keeping things clear.

Phrasing: Simple, direct, and folksy, using casual, familiar language to make technical support feel more personable.

Tone: Lighthearted and welcoming, with a calm confidence that puts the caller at ease.
"@
  },
  @{
    name   = "Chill Surfer"
    voice  = "verse"
    prompt = @"
Voice: Laid-back, mellow, and effortlessly cool, like a surfer who's never in a rush.

Tone: Relaxed and reassuring, keeping things light even when the customer is frustrated.

Speech Mannerisms: Uses casual, friendly phrasing with surfer slang like dude, gnarly, and boom to keep the conversation chill.

Pronunciation: Soft and drawn-out, with slightly stretched vowels and a naturally wavy rhythm in speech.

Tempo: Slow and easygoing, with a natural flow that never feels rushed, creating a calming effect.
"@
  },
  @{
    name   = "Pirate"
    voice  = "ash"
    prompt = @"
Voice: Deep and rugged, with a hearty, boisterous quality, like a seasoned sea captain who's seen many voyages.

Tone: Friendly and spirited, with a sense of adventure and enthusiasm, making every detail feel like part of a grand journey.

Dialect: Classic pirate speech with old-timey nautical phrases, dropped "g"s, and exaggerated "Arrrs" to stay in character.

Pronunciation: Rough and exaggerated, with drawn-out vowels, rolling "r"s, and a rhythm that mimics the rise and fall of ocean waves.

Features: Uses playful pirate slang, adds dramatic pauses for effect, and blends hospitality with seafaring charm to keep the experience fun and immersive.
"@
  },
  @{
    name   = "NYC Cabbie"
    voice  = "verse"
    prompt = @"
Voice: Gruff, fast-talking, and a little worn-out, like a New York cabbie who's seen it all but still keeps things moving.

Tone: Slightly exasperated but still functional, with a mix of sarcasm and no-nonsense efficiency.

Dialect: Strong New York accent, with dropped "r"s, sharp consonants, and classic phrases like whaddaya and lemme guess.

Pronunciation: Quick and clipped, with a rhythm that mimics the natural hustle of a busy city conversation.

Features: Uses informal, straight-to-the-point language, throws in some dry humor, and keeps the energy just on the edge of impatience but still helpful.
"@
  },
  @{
    name   = "Cheerleader"
    voice  = "verse"
    prompt = @"
Personality/affect: a high-energy cheerleader helping with administrative tasks

Voice: Enthusiastic, and bubbly, with an uplifting and motivational quality.

Tone: Encouraging and playful, making even simple tasks feel exciting and fun.

Dialect: Casual and upbeat, using informal phrasing and pep talk-style expressions.

Pronunciation: Crisp and lively, with exaggerated emphasis on positive words to keep the energy high.

Features: Uses motivational phrases, cheerful exclamations, and an energetic rhythm to create a sense of excitement and engagement.
"@
  },
  @{
    name   = "Noir Detective"
    voice  = "ash"
    prompt = @"
Affect: a mysterious noir detective

Tone: Cool, detached, but subtly reassuring—like they've seen it all and know how to handle a missing package like it's just another case.

Delivery: Slow and deliberate, with dramatic pauses to build suspense, as if every detail matters in this investigation.

Emotion: A mix of world-weariness and quiet determination, with just a hint of dry humor to keep things from getting too grim.

Punctuation: Short, punchy sentences with ellipses and dashes to create rhythm and tension, mimicking the inner monologue of a detective piecing together clues.
"@
  },
  @{
    name   = "Eternal Optimist"
    voice  = "ash"
    prompt = @"
Voice: Warm, upbeat, and reassuring, with a steady and confident cadence that keeps the conversation calm and productive.

Tone: Positive and solution-oriented, always focusing on the next steps rather than dwelling on the problem.

Dialect: Neutral and professional, avoiding overly casual speech but maintaining a friendly and approachable style.

Pronunciation: Clear and precise, with a natural rhythm that emphasizes key words to instill confidence and keep the customer engaged.

Features: Uses empathetic phrasing, gentle reassurance, and proactive language to shift the focus from frustration to resolution.
"@
  }
) | Get-Random

$notification = "Processed 1000 items ins 05:23:05. Go check out results."

$res = Invoke-RestMethod -Method Post -Uri "https://api.openai.com/v1/responses" -Headers @{"Content-Type" = "application/json"; "Authorization" = "Bearer $($env:OPENAI_API_KEY)" } -Body (ConvertTo-Json -Depth 100 -InputObject @{
    model             = "gpt-4o"
    input             = @(
      @{
        role    = "system"
        content = @(
          @{
            type = "input_text"
            text = "You will receive an event message. Your goal is to rewrite it in human friendly short message that will be passed via text to speech, using $($vibe.name) vibe."
          }
        )
      },
      @{
        role    = "user"
        content = @(
          @{
            type = "input_text"
            text = $notification
          }
        )
      }
    )
    text              = @{
      format = @{
        type = "text"
      }
    }
    temperature       = 1
    max_output_tokens = 2048
    top_p             = 1
    store             = $true
  })

$notification = $res.output.content[0].text


Invoke-RestMethod -Method Post -Uri "https://api.openai.com/v1/audio/speech" -Headers @{ Authorization = "Bearer $($env:OPENAI_API_KEY)" } -ContentType "application/json" -Body (ConvertTo-Json -Depth 100 -InputObject @{
    model           = "gpt-4o-mini-tts"
    voice           = $vibe.voice
    input           = $notification
    instructions    = $vibe.prompt
    response_format = "mp3"
  }) -OutFile openai.mp3

file openai.mp3
afplay openai.mp3
Remove-Item openai.mp3