Turn text into natural speech. Download an MP3 or a captioned audiogram.
Paste what you want spoken. Line breaks become short pauses.
0 characters โข ~0 seconds of audio
Choose a voice, describe your own, or upload a recording
Top quality (grade A), high pitch, steady pace
Top quality (grade A-), high pitch, steady pace
Good quality (grade B-), mid pitch, slow pace
Good quality (grade B-), mid pitch, steady pace
Fair quality (grade C+), mid pitch, steady pace
Fair quality (grade C+), low pitch, steady pace
Fair quality (grade C+), high pitch, steady pace
Fair quality (grade C+), mid pitch, steady pace
Fair quality (grade C+), mid pitch, steady pace
Fair quality (grade C+), mid pitch, steady pace
Fair quality (grade C), low pitch, fast pace
Fair quality (grade C), low pitch, fast pace
Fair quality (grade C), high pitch, steady pace
Fair quality (grade C), mid pitch, fast pace
Fair quality (grade C), higher pitch, steady pace
Fair quality (grade C-), low pitch, steady pace
Basic quality (grade D+), deep pitch, steady pace
Basic quality (grade D), high pitch, fast pace
Basic quality (grade D), mid pitch, fast pace
Basic quality (grade D), mid pitch, fast pace
Basic quality (grade D), higher pitch, fast pace
Basic quality (grade D), mid pitch, fast pace
Basic quality (grade D), deep pitch, fast pace
Basic quality (grade D), high pitch, steady pace
Basic quality (grade D), high pitch, steady pace
Basic quality (grade D), mid pitch, fast pace
Basic quality (grade D-), higher pitch, steady pace
Basic quality (grade F+), mid pitch, steady pace
Dynamic male voice, native English
Sunny American male voice, native English
Bright, slightly edgy young female, native Chinese
Warm, gentle young female, native Chinese
Seasoned male, low and mellow, native Chinese
Youthful Beijing male, native Chinese
Lively Chengdu male, Sichuan dialect
Playful, light female, native Japanese
Warm, emotional female, native Korean
Clear and warm English female
Bright and expressive English female
Friendly and natural English male
Deep and confident English male
Sweet and clear Chinese female
Gentle and elegant Chinese female
Casual and fresh Chinese male
Steady and warm Chinese male
Edit the generated script directly for advanced customization
Paste your text, pick a voice and keep the output on "Audio (MP3)". When the render finishes, click Download MP3. The audio is the same quality as the voice previews.
Yes. Open "Design Voice" and write who is speaking: age, accent, how their voice sounds, how fast they talk and their attitude. The voice is built from that description. It is a premium engine and costs more credits per character than preset voices.
An audiogram is a video of your narration with word-synced captions over a plain colour, image or looping clip. It lets you post voiceovers, podcast snippets or quotes on TikTok, Reels and YouTube Shorts, where audio alone can't go.
New accounts can try one generation free. After that, audio is billed in credits by the number of characters, so short clips cost very little.
Yes. You keep full ownership and commercial rights to the audio and videos you create, including for monetised YouTube channels, ads and client work.
Preset voices cover English (American and British), Chinese, Japanese and Korean. Voice design works best in English and Chinese.
Receive an email once your audio has finished rendering.
1 credit
Ctrl+Enter creates ยท Ctrl+S saves the draft
A preset voice, and three built from a written description
Heart (preset voice)
Warm and engaging narrator
Designed: documentary narrator
"A British man in his 50s with a warm, resonant baritone, speaking at a calm, measured pace..."
Designed: creepy whisper
"An older man with a low, breathy, gravelly voice, speaking slowly in a near whisper..."
Designed: hype YouTuber
"An American man in his 20s with a bright, punchy voice, speaking fast and loud..."