YOUR VOICE, READY TO SPEAK
AI Voice Production & Personal Voice Modelling
Your words.
Your own voice.
For courses, service introductions and regular content. Build an AI model from your own voice and turn your scripts into narration.
Initial JPY 10,000 / returning JPY 3,000 for 300 Japanese characters / 3 audio revisions
01 YOUR VOICE02 YOUR SCRIPT03 NARRATION04 AUDIO DELIVERY
A FAMILIAR VOICE, MORE POSSIBILITIES
Let your message carry
a familiar voice.
The script is ready, but recording takes time. A tired voice can mean repeated takes. AI narration offers another way to produce your content. I review the recording and script, then refine pronunciation and pacing.
- Course and learning narration
- Product and service audio introductions
- Voice tracks for social posts, videos and regular content
LISTEN TO THE VOICE
Start with the sound.
These two videos demonstrate voice and avatar presentation. Listen for the voice, pacing and pauses.
Voice & Avatar Sample 02
Watch on YouTube ↗The base package delivers audio files. An avatar video like the samples is available as the optional production service below.
VOICE PRODUCTION
Voice Production Pricing
Start by creating your voice model. Further narration is priced by script length.
FIRST VOICE PACKAGE
Initial Voice Model + Narration
10,000 JPY
Modelling JPY 7,000 + narration JPY 3,000 / up to 300 Japanese characters
Request a Free Quote ↗Included in the Base Package
- Reference audio review
- Personal voice model creation
- Narration up to 300 Japanese characters
- Pronunciation, pacing and level adjustment
- Three audio revision rounds
- WAV or MP3 delivery
- SCHEDULE
- Audio production: approximately three days after assets and script are approved, depending on scope.
Returning-client pricing requires an available existing model. Japanese character counts include punctuation and exclude spaces and line breaks; extras are rounded up to 50-character blocks. Other languages, scriptwriting, translation and another voice are quoted separately. Model management, access period and any third-party platform fees are agreed before work begins.
OPTIONAL / AVATAR VIDEO
Add a face to your voice.
Add a talking-avatar video for introductions or explanations. Video production is charged separately from audio.
Final video up to 30 seconds
＋10,000 JPY
Final video up to 60 seconds
＋15,000 JPY
Final video up to 120 seconds
＋25,000 JPY
Over 120 seconds: +JPY 10,000 per additional started 60-second block.
Included in the Video Fee
- One avatar and one background
- Lip sync to the audio and simple captions
- One MP4 format: landscape 16:9 or portrait 9:16
- Two video revision rounds within the agreed script and direction
PRICE EXAMPLE
Initial Voice + Avatar Video up to 60 Seconds
Total JPY 25,000
JPY 10,000 for initial audio + JPY 15,000 for video, with a script up to 300 Japanese characters. Additional fees apply if the video exceeds 60 seconds or the script exceeds 300 characters.
Pricing is based on the duration of one finished video. Multiple avatars, background changes, complex actions, extra formats or language versions are quoted separately. Asset requirements and delivery dates are agreed after review. Personal likenesses require consent and any necessary verification.
FROM YOUR RECORDING TO YOUR MESSAGE
How It Works
- 01
Discuss the brief
Share the use, script length, language, deadline and whether you need an avatar.
- 02
Provide your recording
Review a clean voice recording and agree the platform, costs and asset handling.
- 03
Build and review
Create the voice model and review pronunciation and pacing. Avatar production follows audio approval.
- 04
Refine and deliver
Deliver the refined WAV or MP3. The optional avatar video is delivered as MP4.
QUESTIONS & ANSWERS
Before You Enquire.
Do returning clients pay less?
Yes. The initial JPY 10,000 consists of JPY 7,000 for voice modelling and JPY 3,000 for narration up to 300 Japanese characters. Reusing the same model removes the modelling fee, so subsequent orders cost JPY 3,000 for up to 300 characters. No monthly contract is required; order per script. A different voice or a model rebuild is quoted before production.
What does the base package deliver?
The base package creates your voice model and narration from a script of up to 300 Japanese characters. Audio is delivered as WAV or MP3. Model management, platform access and any ongoing costs are agreed before production. Downloadable model weights and perpetual access are not guaranteed.
How much reference audio is needed?
Please provide a clean recording of your own voice without music or background noise. At least 10 seconds is a starting point; around three minutes is preferable. A new recording may be needed depending on quality.
How are script length and extra fees calculated?
Japanese scripts include punctuation but exclude spaces and line breaks. Beyond the first 300 characters, add JPY 500 per started block of 50 characters. Returning clients pay JPY 3,000 for up to 300 characters, then the same additional rate. English and other languages are quoted after script review.
Can I add an avatar video?
Yes. Avatar production is charged by final video duration in addition to the audio fee. It includes one avatar, one background, lip sync and simple captions. A personal likeness requires consented visual assets and identity verification when required.
Can I clone someone else’s voice?
This service is for the client’s own voice. Impersonation and unauthorized replication of another person’s voice are not accepted.
What about revisions and emotional expression?
Audio includes three revision rounds within the approved script and direction. Subtle emotion and acting may not be reproduced exactly. Script replacement, a new voice direction or reworking approved content is quoted separately. Avatar video includes two revision rounds.
LET YOUR VOICE BEGIN
Enquire About AI Voice Production
What would you like your voice to say, and where? You can enquire before the script or project length is decided.
Enquiries and quotes are free. Voice recordings and photos are requested after production terms are agreed.