Voice Options
ADD CREATE uses high-fidelity neural voices for all audio narration. Voice selection happens during the Render step when you submit your script for synthesis.
Available Voices
Section titled “Available Voices”Seven voices are available. You can preview any of them before committing to a render:
| Voice | Gender | Character | Best For |
|---|---|---|---|
| Achernar | Female | Professional, steady, clear | News-style narration, formal content |
| Aoede | Female | Warm, engaging, expressive | Storytelling, educational content |
| Charon | Male | Deep, authoritative, calm | Serious topics, in-depth analysis |
| Fenrir | Male | Energetic, youthful, vibrant | Fast-paced or upbeat content |
| Kore | Female | Bright, friendly, approachable | Casual discussions, FAQs |
| Puck | Male | Playful, light, conversational | Debate formats, informal pieces |
| Zephyr | Female | Smooth, sophisticated, calm | Executive summaries, corporate content |
Voice Assignment
Section titled “Voice Assignment”For dialogue formats (Deep Dive and Debate), two voices are used:
- Voice A is the primary voice — used for the first speaker and for all narration in single-speaker formats.
- Voice B is the second speaker in dialogue formats.
The default pairing is Achernar (Voice A) and Puck (Voice B). You can change either voice in the render settings.
Supported Languages
Section titled “Supported Languages”| Language | |
|---|---|
| English (US) | |
| Spanish | |
| French | |
| German | |
| Japanese | |
| Korean | |
| Mandarin Chinese |
Output Format
Section titled “Output Format”When rendering, you can choose the file format for the audio output:
| Format | Description |
|---|---|
| WAV | Uncompressed — highest quality, larger file size |
| MP3 | Compressed — good balance of quality and size |
| OGG | Compressed — well suited for streaming |
Audio Settings
Section titled “Audio Settings”You can also adjust the following when rendering:
- Speed — how fast the voices speak. The default is normal speed; you can go slightly faster or slower.
- Volume — raise or lower the output volume if needed.
Advanced Usage Notes
Section titled “Advanced Usage Notes”Use these patterns to get more predictable results:
- Keep inputs specific and scoped to one intent per generation request.
- Save intermediate outputs often, especially before running major edits or regenerations.
- Use review and assignment workflows early to reduce rework late in the lifecycle.
Troubleshooting
Section titled “Troubleshooting”If results are not what you expected:
- Verify source quality first (missing context, inconsistent structure, or conflicting inputs reduce output quality).
- Re-check selected options and audience/profile settings before re-running.
- If a job fails repeatedly, wait briefly and retry once; then escalate with the artifact or job context.
Frequently Asked Questions
Section titled “Frequently Asked Questions”Why did quality change between runs?
Section titled “Why did quality change between runs?”Different input context, settings, and model/runtime conditions can produce different outputs.
Should I regenerate or manually edit?
Section titled “Should I regenerate or manually edit?”Regenerate when the core structure is wrong; manually edit when only wording, ordering, or style needs adjustment.
What is the best way to reduce iteration cycles?
Section titled “What is the best way to reduce iteration cycles?”Start with clear scope, run smaller batches, and use review checkpoints after each major step.