Coqui·Audio — weighted competency·Tue 2 Jun 2026
CCoqui XTTS-2
Coqui XTTS-2 scores 68/100 competency for Audio at $3.00.
Low confidenceOpen weights
Competency
68/100
category rank #6
Cost
$3.00/ 1M chars
blended
Speed
76/100
Moderate
Accuracy
4.4% halluc.
Medium confidence
Score history.
Weighted Audio competency · last 12 weeks · weekly snapshot.
68/100
— flat
What it's actually good at.
Score on each business-task subset that goes into the weighted competency.
Text-to-Speech35% of category weight
63
Voice Cloning25% of category weight
67
Multilingual20% of category weight
71
Real-time Conversation20% of category weight
75
Best for. Watch out for.
✓ Best for
- Strong at Text-to-Speech for Coqui.
- Strong at Voice Cloning for Coqui.
⚠ Watch out for
- Accuracy 4.4% — verify outputs.
- Validate fit for your specific workload before committing.
Pricing.
Published usage pricing. Figures refresh daily from our pricing sources.
$3.00
Usage pricing
$3.00/1M tok
- Input
- $3.00 / 1M tokens
- Output
- $9.00 / 1M tokens
Where it sits.
Position against the rest of the category. Ranked by weighted competency.
| Rank | Model | Score | Cost | Speed | Δ vs Coqui |
|---|---|---|---|---|---|
| 01 | CCartesia Sonic | 100 | $50.00 | 96 / 100 | +32 |
| 02 | EElevenLabs v3 | 41 | $150.00 | 90 / 100 | -27 |