Leaderboard / www.trezalabs.com / endpoint
POST https://www.trezalabs.com/api/x402/speech
Scores measure reliability and honesty, not output quality.
- Listed only 1 day ago; new listings earn trust over 30 days.
- Answered all 6 probes in the last 7 days.
- Category
- Image generation by llm, confidence 30%
- Latest quote
- $0.04 on Base to 0xaE39…b42C
- Uptime
- 100% / 7d, 100% / 30d
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 2h ago
- Next probe
- 2026-11-17 16:39 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| payai | exact | Solana | EPjFWd…Dt1v | 20000 | EX4MyY…foGd | default | yes | 5h ago |
| cdp | exact | Base | 0x8335…2913 | $0.04 | 0xaE39…b42C | default | yes | 5h ago |
| cdp | exact | Solana | EPjFWd…Dt1v | 40000 | EX4MyY…foGd | default | yes | 5h ago |
Listing changes
| When | Event | From | To |
|---|---|---|---|
| 27h ago | description_changed | Text to speech (AI voice generation): send text, get a natural ElevenLabs voiceover MP3 back in the same response. Use it when an agent needs narration, a voiceover for a video, or a spoken version of text. Eleven v3 (expressive, takes [whispers]-style directions) or Multilingual v2 (29 languages), a choice of ElevenLabs narrators, up to 3000 characters, $0.42 per 1,000 characters. GET this URL for the voices. No account or API key: the payment is the only credential. | Text to speech (AI voice generation): send text, get an ElevenLabs voiceover MP3 back in the same response. Use it when an agent needs narration, a voiceover for a video, or a spoken version of text. Eleven v3 (expressive: [whispers]-style directions, an emotion) or Multilingual v2 (29 languages), ElevenLabs narrators, adjustable pitch and volume, up to 3000 characters, $0.42 per 1,000 characters. GET this URL for the voices. No account or API key: the payment is the only credential. |
| 27h ago | description_changed | Text to speech (AI voice generation): send text, get a natural ElevenLabs voiceover MP3 back in the same response. Use it when an agent needs narration, a voiceover for a video, or a spoken version of text. Eleven v3 (expressive, takes [whispers]-style directions) or Multilingual v2 (29 languages), a choice of ElevenLabs narrators, up to 3000 characters, $0.42 per 1,000 characters. GET this URL for the voices. No account or API key: the payment is the only credential. | Text to speech (AI voice generation): send text, get an ElevenLabs voiceover MP3 back in the same response. Use it when an agent needs narration, a voiceover for a video, or a spoken version of text. Eleven v3 (expressive: [whispers]-style directions, an emotion) or Multilingual v2 (29 languages), ElevenLabs narrators, adjustable pitch and volume, up to 3000 characters, $0.42 per 1,000 characters. GET this URL for the voices. No account or API key: the payment is the only credential. |
Paid probes
No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.
Delivery checks
Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Delivery results do not affect scores yet.
No delivery checks yet. They run inside the weekly paid probe.
Classification history
Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 11h ago | Image generation | 30% | llm | v1 | claude-haiku-5-5: Text-to-speech returns an MP3 voiceover; no existing category covers audio generation. The closest fit is image_gen as a generative media modality, but it is a poor match, so confidence is low and 'other' is arguably more accurate. |
| 15h ago | Inference | 60% | rules | v1 | rule inference matched "whisper" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 2h ago | free | 402 | 154 ms | v2 | yes | $0.04 | 0xaE39…b42C | — |
| 8h ago | free | 402 | 145 ms | v2 | yes | $0.04 | 0xaE39…b42C | — |
| 14h ago | free | 402 | 215 ms | v2 | yes | $0.04 | 0xaE39…b42C | — |
| 20h ago | free | 402 | 112 ms | v2 | yes | $0.04 | 0xaE39…b42C | — |
| 27h ago | free | 402 | 124 ms | v2 | yes | $0.04 | 0xaE39…b42C | — |
| 33h ago | free | 402 | 1048 ms | v2 | yes | $0.04 | 0xaE39…b42C | — |