Creating Voice Profiles

Overview

A voice profile is a saved voice you can reuse across generations, stories, and the API. As of 0.4, Voicebox profiles come in two flavors that map to two different ways of getting a voice:

Profile type What it stores Use when…
Cloned One or more reference audio samples + a voice embedding You want to replicate a specific person's voice
Preset A reference to a pre-built voice in a specific engine You want a curated, production-ready voice with no audio prep

Both types live in the same Profiles tab and behave the same way at generation time — pick the type that matches your goal and follow the workflow below.

Not sure which to use? Cloning gives you a *specific* voice but needs clean audio. Preset gives you *good* voices instantly but you don't get to choose who they sound like.

Workflow A — Cloned Profiles

Use this when you want to replicate a specific person's voice from a recording.

Prepare Audio

10-30 seconds of clear speech, minimal background noise. See Voice Cloning for the engine catalog.

Create Profile

Profiles → + New Profile → choose a cloning engine (Qwen3-TTS, Chatterbox Multilingual, Chatterbox Turbo, LuxTTS, or TADA)

Upload or Record Sample

Drag in an audio file, or record directly with the in-app recorder

Generate to Test

Use the profile to generate a test phrase. If quality is poor, add more samples

Audio Requirements (Cloning Only)

Duration

10-30 seconds

Too short: Poor quality Too long: Unnecessary

Clarity

Clear speech

No background noise No music or overlapping voices

Quality

High fidelity

44.1 kHz or 48 kHz sample rate Minimal compression

Content

Natural speech

Conversational tone Complete sentences

File Formats

Supported formats:

  • WAV (recommended) — Lossless quality
  • MP3 — Acceptable, minimal compression
  • M4A — Acceptable
  • FLAC — Lossless alternative
Use WAV for best results. Avoid heavily compressed formats.

Recording Tips

Quiet Space
  • Record in a quiet room
  • Turn off fans, AC, appliances
  • Close windows to reduce outside noise
  • Use soft furnishings to reduce echo
Microphone Placement
  • 6-12 inches from mouth
  • Slight angle to reduce plosives (p, b, t)
  • Use a pop filter if available
  • Maintain consistent distance
Recording Settings
  • 44.1 kHz or 48 kHz sample rate
  • 16-bit or 24-bit depth
  • Mono is fine (stereo will be converted)
  • Avoid automatic gain control

Speaking Style

  • Natural pace — Don't rush or speak too slowly
  • Clear articulation — Pronounce words clearly
  • Consistent volume — Maintain steady loudness
  • Normal tone — Speak as you normally would
  • Complete sentences — Avoid fragments or "ums"

Multiple Samples

Adding multiple samples can significantly improve quality:

Robustness

Model learns a more complete representation

Versatility

Handles different speaking styles better

Quality

Reduces artifacts and improves naturalness

Consistency

More reliable across different texts

Consider adding samples with:

  1. Different tones — casual, formal, excited, calm
  2. Different content — narratives, questions, statements
  3. Different recording conditions — studio quality, room acoustics
All samples should be from the **same speaker**. Mixing voices will produce poor results.

Processing Existing Audio

If you have existing audio (podcasts, videos, etc.):

Find Clean Speech

Look for segments with just the target speaker, no background music, minimal noise

Use Audio Editor

Tools like Audacity or Adobe Audition: cut clean 10-30s segments, remove silence at start/end, normalize volume

Export as WAV

Save as high-quality WAV file

For light background noise, use Audacity's noise reduction (gentle settings — over-processing introduces artifacts).

Testing & Iteration

After creating a cloned profile:

Generate Test

Try a simple phrase: "Hello, this is a test of my voice profile."

Evaluate Quality

Listen for natural tone, clear pronunciation, proper prosody, lack of artifacts

Iterate

If quality is poor: add more samples, try different source audio, check sample quality

Common Issues

Robotic Voice

Cause: Poor quality samples or too short

Fix: Use longer, higher-quality samples

Wrong Tone

Cause: Sample tone doesn't match desired output

Fix: Record samples in the style you want to generate

Artifacts/Glitches

Cause: Background noise or audio issues in samples

Fix: Clean up samples or re-record in quieter environment

Workflow B — Preset Profiles

Use this when you want a ready-made voice without recording anything. Available engines: Kokoro 82M (50 voices) and Qwen CustomVoice (9 voices). See Preset Voices for the full catalog.

Create Profile

Profiles → + New Profile → choose Kokoro or Qwen CustomVoice as the engine

Pick a Voice

The engine's voice catalog appears. Click any voice to preview it

Name and Save

Give the profile a name. No audio sample required

Generate

The profile is ready immediately — use it in the floating generate box or Generate page

Preset profiles are **locked to their source engine**. Switching to a different engine in the floating generate box greys out the profile, since the voice only exists in that engine. Clicking a greyed profile auto-switches the engine back.

Qwen CustomVoice + Instruct

Preset voices in Qwen CustomVoice support delivery instructions — natural-language style control over tone, pace, and emotion. The floating generate box shows a slider icon next to the generate button when a Qwen CustomVoice profile is selected; click it to reveal the instruct textarea.

See Preset Voices → Using Instruct Mode for examples.

Advanced Tips

Celebrity / Character Voices (Cloning)

For cloning public figures or characters:

  1. Legal considerations — Ensure you have rights or it's clearly fair use
  2. Source quality — Find high-quality interview audio or clean clips
  3. Consistency — Use clips where they speak similarly
  4. Multiple samples — Very important for recognizable voices

Accent & Dialect (Cloning)

Cloning models preserve accent and dialect:

  • British English samples generate British English output
  • Southern accent samples produce Southern accent output
  • Regional pronunciations are maintained

Emotion Transfer (Cloning)

The emotional tone of samples affects generation:

  • Energetic samples → energetic output
  • Calm samples → calm output
  • Mix samples for a more versatile profile

For Qwen CustomVoice presets, use the instruct field instead of relying on sample emotion — that's exactly what it controls.

Managing Profiles

Organization

  • Descriptive names — "John Smith - Professional Narrator"
  • Add descriptions — Note recording conditions, use cases, or which preset voice
  • Language tags — Mark the primary language
  • Archive unused — Keep profile list manageable

Export / Import

  • Export profiles to share or backup
  • Import from colleagues or teammates
  • Cloned profiles export with their voice embeddings (not the original audio)
  • Preset profiles export as engine + voice ID metadata only — the importer must have that engine's model installed

Next Steps