Text to Speech AI Generator
Generated on PixelDojo with Text to Speech. Produced by PixelDojo's generation pipeline.
Text to Speech costs 0.5 credits for any script up to 187 words, then scales up from there at 2 credits per 750 words. A 375-word script costs exactly 1 credit, and a full 750-word script costs 2 credits. This page reads the word-count formula, the floor, and the voice and format controls straight out of the pricing code.
The exact pricing and what you can control
The floor: 0.5 credits up to 187 words
The formula is 2 credits per 750 words, rounded up to the nearest 0.1 credit, with a 0.5 credit minimum. That minimum is what you pay for anything from a single word up to 187 words.
Past the floor, it climbs in 0.1 credit steps
188 words costs 0.6 credits, 200 words also 0.6, and the price keeps stepping up by tenths of a credit as the word count rises.
Round numbers to check against
375 words costs exactly 1 credit. 750 words costs exactly 2 credits. 1,500 words costs exactly 4 credits. The rate is flat at 2 credits per 750 words once you are past the floor.
Ten emotion presets, not just a voice pick
Beyond the voice_id itself, an emotion field takes auto, happy, sad, angry, fearful, disgusted, surprised, calm, fluent, or neutral, layered on top of whatever voice you choose.
Format, sample rate, and channel are all yours to set
Output as mp3, wav, flac, or pcm, at a sample rate up to 44,100 Hz, in mono or stereo, plus independent speed (0.5x to 2x), volume, and pitch (plus or minus 12 semitones) controls.
Word-aligned subtitles on request
Set subtitle_enable to true and the response includes subtitles aligned to the words, useful for captioning the same audio you just generated.
0.5 credits covers up to 187 words. Past that, the rate is 2 credits per 750 words, read from the pricing function itself.
Why Choose Pixel Dojo for Text to Speech
Professional-quality results with cutting-edge AI technology
0.5 credits for most short scripts
Anything up to 187 words, which covers a typical intro line or a short announcement, costs the flat minimum.
Priced by words, not by the clock
The charge is set from your script's word count before generation, so the cost is known before you submit the job.
Full audio controls in one request
Voice, emotion, speed, pitch, volume, format, sample rate, and channel count are all set on the same call.
How It Works
How a Text to Speech job gets priced before it runs:
Write the script
Up to 10,000 characters. The word count in this text is the only thing that moves the price.
The platform counts words and applies the floor
2 credits per 750 words, rounded up to the nearest 0.1 credit, with a 0.5 credit minimum that covers up to 187 words.
Run it in the app or over the API
From the tool page, or POST to /api/v1/models/text-to-speech/run with your key, setting voice_id, emotion, and format as needed.
Loved by creators on PixelDojo
Real feedback from people using PixelDojo, pulled from our in-product surveys.
Practically every Ai suite in one place? Who wouldn't?
versatile menu of tools
Best AI tool availble the suite is rad
Versatility quality, value, ROI, innovation
variety of tools available and prompt tools
A "one-stop-shop" for creators! Thanks!!
Explore more AI tools on PixelDojo
AI Tools
Compare & Switch
- Best AI Image Generators
- Best AI Video Generators
- Midjourney Alternatives
- Civitai Alternatives
- Runway Alternatives
- Leonardo Alternatives
- Pika Alternatives
- Luma Alternatives
- Magnific Alternatives
- Veo Alternatives
- Flux Alternatives
- Freepik Alternatives
- Seedance Alternatives
- Seedream Alternatives
- Pixverse Alternatives
- GPT Image Alternatives
- Synthesia Alternatives
- Playground Alternatives
- NightCafe Alternatives
- Canva AI Alternatives
- ElevenLabs Alternatives
- ComfyUI Alternatives
- Fal Alternatives
- Replicate Alternatives
Common Questions
Everything you need to know about Text to Speech
What does Text to Speech cost?
0.5 credits for any script up to 187 words. Past that it is 2 credits per 750 words, rounded up to the nearest 0.1 credit, so 375 words is 1 credit and 750 words is 2 credits.
How many words fit in the minimum charge?
187 words. At 188 words the price steps up to 0.6 credits, and it keeps climbing by tenths of a credit as the word count rises.
Does voice choice or emotion change the price?
No. voice_id, the emotion preset, speed, pitch, volume, format, sample rate, and channel count are all free to set. Only the word count in your text moves the price.
How does it differ from Text to Music?
Text to Speech is priced by word count and floors at 0.5 credits. Text to Music is priced by seconds of a finished track and floors at 6 credits for its 30-second minimum. They are built for different jobs: narration versus a musical bed.
Can I get subtitles with the audio?
Yes. Set subtitle_enable to true and the response includes subtitles aligned to the words in your script, at no extra credit cost.
How do I call it from the API?
POST to /api/v1/models/text-to-speech/run with your API key and a text field. voice_id defaults to Wise_Woman if you do not set one.