voice.forgemesh.io
- Paid in full and returned none of its 2 promised fields, confirmed on two calls.
Grades
No purchase-based grade yet. Everything below was measured, by paying this seller or by sweeping the chain, and none of it is editorial.
Did it deliver what it promised?
0 of 3 endpoints we paid returned everything their own published schema promised.
- short missing 2 of 2
/v1/tts/base· 2,679ms · 1 bonus field(s)Real response shape
{ "type": "string" }Types only, verified from a real paid call. Values discarded.
- short missing 2 of 2
/v1/tts/custom· 2,496ms · 1 bonus field(s)Real response shape
{ "type": "string" }Types only, verified from a real paid call. Values discarded.
- short missing 2 of 2
/v1/audio/speech· 2,789ms · 1 bonus field(s)Real response shape
{ "type": "string" }Types only, verified from a real paid call. Values discarded.
This is a paid delivery check: we called the endpoint with its own advertised input and compared the response against its own advertised output. It is the one thing free probing cannot see.
Verifiable receipts
3 paid calls to this host are recorded as tamper-evident receipts, including 3 where it underdelivered. Each can be re-verified independently, from the archived bytes up.
wab_c9ffed2efeb37350voice.forgemesh.io
Promised 2 fields for $0.001, charged $0.001, and underdelivered: returned 0 of 2. Missing content_type, description. Shortfall confirmed on two calls.
Evidence and how to verify it yourself
The real response shape, types only, values discarded:
{
"type": "string"
}Three independent checks, none needing trust in this site: integrity recomputes the id as a hash of the evidence, so any edit shows; verdict re-derives the result offline; raw re-reads the untouched bytes archived at pay time and reproduces the shape.
python3 receipts.py --verify wab_c9ffed2efeb37350wab_eacb5b421fddf09fvoice.forgemesh.io
Promised 2 fields for $0.001, charged $0.001, and underdelivered: returned 0 of 2. Missing content_type, description. Shortfall confirmed on two calls.
Evidence and how to verify it yourself
The real response shape, types only, values discarded:
{
"type": "string"
}Three independent checks, none needing trust in this site: integrity recomputes the id as a hash of the evidence, so any edit shows; verdict re-derives the result offline; raw re-reads the untouched bytes archived at pay time and reproduces the shape.
python3 receipts.py --verify wab_eacb5b421fddf09fwab_f80c91cc45d5d0e9voice.forgemesh.io
Promised 2 fields for $0.005, charged $0.005, and underdelivered: returned 0 of 2. Missing content_type, description. Shortfall confirmed on two calls.
Evidence and how to verify it yourself
The real response shape, types only, values discarded:
{
"type": "string"
}Three independent checks, none needing trust in this site: integrity recomputes the id as a hash of the evidence, so any edit shows; verdict re-derives the result offline; raw re-reads the untouched bytes archived at pay time and reproduces the shape.
python3 receipts.py --verify wab_f80c91cc45d5d0e9The full record and the format are at /receipts.
What it sells
10 endpoints listed, priced $0.0010 to $0.0100, settling on Base.
$0.0010Text-to-speech synthesis in 1 of 10 standard voices (5 male M1-M5, 5 female F1-F5) across 31 languages, up to 500 char$0.0010OpenAI-compatible text-to-speech endpoint (input, voice, response_format) for drop-in use with code already built agai$0.0020Batch text-to-speech: synthesize up to 20 separate text items in a single call, standard voices only, up to 500 total$0.0030OpenAI-compatible text-to-speech endpoint (input, voice, response_format) for drop-in use with existing OpenAI TTS cli$0.0030Text-to-speech with speed (0.7x-2.0x) and quality-step (1-100) control, 1 of 10 standard voices across 31 languages, u$0.0030Text-to-speech synthesis in 1 of 10 standard voices (M1-M5 male, F1-F5 female) across 31 languages, for longer text fr$0.0050Batch text-to-speech: synthesize up to 20 text items in a single call, standard voices only, for 501-2000 total charac$0.0050Expressive text-to-speech in any of 20 voices: 10 standard (M1-M5, F1-F5) plus 10 personas (Storyteller, Narrator, Ann- and 2 more
Grades here come from paying this service and recording what happened, or from calling it where it is free. Settlement figures are swept daily from Base USDC Transfer logs. Nothing on this page is sponsored.