AI voice generator and text to speech in English and Chinese
AI text to speech turns a written script into audio you can play and download. The MiMo V2.5 voice studio supports preset voices, voice design and reference-based voice cloning. For a first narration, choose a preset and start with a short English or Chinese script.
Open toolUpdated
- What you provide
- A spoken script, a preset voice and optional instructions for emotion, pace or character delivery.
- What you get
- Private speech recordings with browser playback, WAV download, script reuse and record deletion.
- Main speech languages
- English and Chinese; six interface languages
- Script and style
- Up to 2,000 characters each
- Export and retention
- WAV · recordings kept for 7 days
- Current offer
- Free for a limited time, no Credits; check the studio
What you can make
Short-video narration
Generate a spoken script, then take the WAV into your own editor to align it with footage.
Product and course explanations
Use short sentences and a clear voice; check numbers, brand names and specialist terms by listening.
Travel stories and podcast excerpts
Narrate a short story in English or Chinese, with delivery instructions kept separate from the script.
How to use it
- Open the voice studio and choose Preset voices. Sign in, check whether the free offer is available and select an English or Chinese voice.
- Enter only the words to be spoken in Script. Check punctuation, numbers and names; the limit is 2,000 characters per request.
- Describe pace, emotion or character in the separate style field. Choose Voice design for a new sound description, or Voice cloning to use an authorized reference recording.
- Generate speech and listen once the task completes. The site sends your script without an extra rewriting step, but pronunciation and omissions still need review.
- Download the WAV when satisfied. Reuse the script to make adjustments and generate again. Recordings are private and kept for 7 days, so download a copy for longer use.
Start with an example
Narrate a short travel film
Put these in their separate Script and Style instructions fields, so the delivery instructions are not part of the spoken text.
- Script
The streets are still quiet. We follow a narrow path into the everyday life of the city. Perhaps the best part of a journey is hidden in these ordinary moments.
- Style instructions
Warm, natural documentary narration. Slightly slow pace with gentle pauses between sentences. Understated and conversational, without a promotional tone.
Check the result: Listen for a clear opening and natural pauses, then compare the duration with your footage. Finish the timing in your video editor.
Open toolCommon questions
Are AI voiceover, text to speech and TTS the same here?
They all describe turning a script into playable speech. Presets provide a quick starting point; voice design describes a new sound, while cloning references an authorized recording.
Does voice generation use Credits?
The voice studio is currently free for a limited time and does not use Credits. Check live availability in the studio. Ordinary AI image generation remains billed by its selected model.
Can it dub my video and export MP4?
The current deliverable is a WAV audio file. Download it into a video editor to combine footage, music and subtitles; the voice studio does not export a finished MP4.
Is my script rewritten before synthesis?
The site does not add a model step to rewrite your script. Script and style instructions are sent separately. The speech model may still vary in pronunciation or pauses, so review the actual audio.