text-to-audio
Inworld 1.5 Mini delivers high-quality text-to-speech synthesis with 56+ multilingual voices, adjustable speaking rate, and natural-sounding audio output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Input
Idle
Your request will cost $0.005 per run.
For $1 you can run this model approximately 200 times.
ExamplesView all
README
Inworld 1.5 Mini Text-to-Speech
Inworld 1.5 Mini is a lightweight, ultra-affordable text-to-speech model that converts written text into natural speech. It offers the same voice selection, speaking rate, and expressiveness controls as the Max model — at half the cost. Perfect for high-volume workflows, prototyping, and budget-conscious production.
- Need higher quality? Try Inworld 1.5 Max Text-to-Speech
Why Choose This?
-
Ultra-low cost Just $0.005 per 1,000 characters — the most affordable option for text-to-speech at scale.
-
Multilingual voice library 65+ voices across 14 languages including English, Chinese, Japanese, Korean, and more.
-
Speaking rate control Adjust the speed of speech to suit narration, dialogue, announcements, or any delivery style.
-
Temperature control Fine-tune expressiveness — lower values for consistent delivery; higher values for more dynamic, varied speech.
-
Fast processing Lightweight architecture delivers quick turnaround, ideal for real-time or high-volume pipelines.
Parameters
| Parameter | Required | Description |
|---|---|---|
| text | Yes | The text content to convert to speech |
| voice_id | No | Voice preset to use (see Available Voices below) |
| speaking_rate | No | Speed of speech (default: 1) |
| temperature | No | Expressiveness level (default: 1) |
Available Voices
English
| Voice ID | Description |
|---|---|
| Alex | Energetic and expressive mid-range male voice, with a mildly nasal quality |
| Ashley | A warm, natural female voice |
| Craig | Older British male with a refined and articulate voice |
| Deborah | Gentle and elegant female voice |
| Dennis | Middle-aged man with a smooth, calm and friendly voice |
| Edward | Male with a fast-talking, emphatic and streetwise tone |
| Elizabeth | Professional middle-aged woman, perfect for narrations and voiceovers |
| Hades | Commanding and gruff male voice, think an omniscient narrator or castle guard |
| Julia | Quirky, high-pitched female voice that delivers lines with playful energy |
| Pixie | High-pitched, childlike female voice with a squeaky quality |
| Mark | Energetic, expressive man with a rapid-fire delivery |
| Olivia | Young, British female with an upbeat, friendly tone |
| Priya | Even-toned female voice with an Indian accent |
| Ronald | Confident, British man with a deep, gravelly voice |
| Sarah | Fast-talking young adult woman, with a questioning and curious tone |
| Shaun | Friendly, dynamic male voice great for conversations |
| Theodore | Gravelly male voice, with a time-worn quality |
| Timothy | Lively, upbeat American male voice |
| Wendy | Posh, middle-aged British female voice |
| Dominus | Robotic, deep male voice with a menacing quality. Perfect for villains |
| Hana | Bright, expressive young female voice, perfect for storytelling and gaming |
| Clive | British-accented male voice with a calm, cordial quality |
| Carter | Energetic, mature radio announcer-style male voice |
| Blake | Rich, intimate male voice, perfect for audiobooks and romantic content |
| Luna | Calm, relaxing female voice, perfect for meditations and sleep stories |
Chinese
| Voice ID | Description |
|---|---|
| Yichen | A calm, flat young adult male Chinese voice |
| Xiaoyin | A youthful Chinese female voice with a gentle, sweet voice |
| Xinyi | A Chinese woman with a neutral tone, perfect for narrations |
| Jing | An energetic, fast-paced young Chinese female |
Japanese
| Voice ID | Description |
|---|---|
| Asuka | Friendly, young adult Japanese female voice |
| Satoshi | Dramatic, expressive male Japanese voice filled with energy |
Korean
| Voice ID | Description |
|---|---|
| Hyunwoo | Young adult Korean male voice |
| Minji | Energetic, friendly young Korean female voice |
| Seojun | Clear, deep mature Korean male voice |
| Yoona | Korean woman with a gentle, soothing voice |
French
| Voice ID | Description |
|---|---|
| Alain | Deep, smooth middle-aged male French voice. Composed and calm |
| Hélène | Middle-aged French woman, with a smooth, musical, and graceful voice |
| Mathieu | A French male voice carrying a nasal quality |
| Étienne | Calm young adult French male |
German
| Voice ID | Description |
|---|---|
| Johanna | A calm older German female with a low, smoky voice |
| Josef | An articulate German male voice with an announcer-like quality |
Spanish
| Voice ID | Description |
|---|---|
| Diego | Spanish-speaking male voice with a soothing, gentle quality |
| Lupita | Vibrant, energetic young Spanish-speaking female voice |
| Miguel | A calm adult Spanish-speaking male voice, perfect for storytelling |
| Rafael | Middle-aged Spanish-speaking male with a deep, composed voice |
Portuguese
| Voice ID | Description |
|---|---|
| Heitor | Composed Portuguese-speaking male voice with a neutral tone |
| Maitê | Middle-aged Portuguese-speaking female voice |
Italian
| Voice ID | Description |
|---|---|
| Gianni | Deep, smooth Italian male voice that speaks rapidly |
| Orietta | Calm adult female Italian voice, with a soothing cadence |
Dutch
| Voice ID | Description |
|---|---|
| Erik | Older Dutch male voice with a weathered edge |
| Katrien | Dutch woman with an expressive voice |
| Lennart | A confident Dutch male voice. Calm and relaxed |
| Lore | Clear, calm Dutch female voice, great for narrations |
Polish
| Voice ID | Description |
|---|---|
| Szymon | Polish adult male voice with a warm, friendly quality |
| Wojciech | A middle-aged Polish male voice |
Russian
| Voice ID | Description |
|---|---|
| Svetlana | Soft, high-pitched female voice, with a slightly breathy quality |
| Elena | Clear, mid-range female voice, with a neutral, informational tone |
| Dmitry | Deep, gravelly male voice, with a commanding and narrative tone |
| Nikolai | Deep, resonant male voice, with a clear, theatrical quality |
Hindi
| Voice ID | Description |
|---|---|
| Riya | Professional and clean female voice, polished and approachable |
| Manoj | Clear, professional Hindi male voice. Great for narrations |
Hebrew
| Voice ID | Description |
|---|---|
| Yael | Mid-range female Hebrew voice, suitable for narrations |
| Oren | Steady male Hebrew voice, great for podcasts and voiceovers |
Arabic
| Voice ID | Description |
|---|---|
| Nour | Polished female Arabic voice with a friendly tone |
| Omar | Bright, confident Arabic male voice, great for announcements |
How to Use
- Enter your text — type or paste the content you want converted to speech.
- Select a voice — choose a voice preset from the voice_id dropdown.
- Adjust speaking rate — slide to control how fast or slow the speech is delivered.
- Adjust temperature — slide to control the expressiveness and variation in delivery.
- Run — submit and download the generated audio.
Pricing
| Characters | Cost |
|---|---|
| Up to 1,000 | $0.005 |
| Up to 2,000 | $0.010 |
| Up to 5,000 | $0.025 |
| Up to 10,000 | $0.050 |
Billing Rules
- Rate: $0.005 per 1,000 characters
- Rounding: character count is rounded up to the next 1,000
Best Use Cases
- High-Volume Production — Generate large batches of audio at minimal cost.
- Prototyping & Testing — Quickly preview voiceovers before committing to final production.
- Chatbots & Virtual Assistants — Add voice output to conversational AI at scale.
- Content Accessibility — Convert written content to audio affordably for wider audiences.
- Game & App Dialogue — Generate character voice lines for interactive experiences on a budget.
- Multilingual Content — Create audio content in 14 languages from a single API.
Pro Tips
- Use Mini for drafting and iteration, then switch to Max for final production if higher quality is needed.
- Keep speaking_rate around 1 for natural pacing; adjust lower for dramatic reads, higher for quick announcements.
- Lower temperature gives more predictable, consistent output — great for automated systems.
- Break long texts into logical paragraphs for better pacing and natural pauses.
- Match voice language to your text language for best pronunciation and intonation.
Notes
- Text is the only required field.
- Billing is based on character count, rounded up to the nearest 1,000.
- For maximum voice quality, consider Inworld 1.5 Max.
Related Models
- Inworld 1.5 Max Text-to-Speech — Higher quality voices at $0.01 per 1,000 characters.