hexgrad
hexgrad: Kokoro 82M
hexgrad/kokoro-82m
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Kokoro 82M (hexgrad/kokoro-82m) is described by the OpenRouter catalog as a lightweight, open-weight text-to-speech model from hexgrad that converts text input into speech output. The catalog reports support for eight languages, including American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese, with a 4096-token context length. All evidence comes from a single catalog listing; an independent model card was not available in this source pack, and no measured performance data was supplied.[1]
Strengths
- The OpenRouter catalog describes it as a lightweight, open-weight text-to-speech model, a reported property rather than a measured result.[1]
- The catalog reports coverage of eight languages: American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese.[1]
- Per the catalog, it accepts text input with a 4096-token context length and produces speech output.[1]
Limitations
- The only evidence is an OpenRouter catalog listing; an independent model card was not available in this source pack, so all claims are unverified catalog statements.[1]
- No benchmark or audio-quality measurements were supplied, so speech naturalness and accuracy require workload validation; details such as available voices, license terms, and hardware requirements are unknown.[1]
Where to use it
- May be worth evaluating as a lightweight, open-weight text-to-speech option for applications needing generated speech, subject to validating quality on real inputs.[1]
- Could suit prototyping multilingual voice features across the eight catalog-listed languages, pending per-language quality checks.[1]
- Potentially relevant for cost-sensitive text-to-speech experiments, since the catalog lists usage-based pricing.[1]
Sources
- [1] OpenRouter catalog · hexgrad: Kokoro 82MSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese)...
Specifications
- Model ID
- hexgrad/kokoro-82m
- Creator
- hexgrad
- Added to OpenRouter
- 23.04.2026
- Context length
- 4,096
- Modality
- text->speech
- Input modalities
- text
- Output modalities
- speech
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfra | 4,096 | — | — | — | — | 100% |
| Together | 4,096 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.