fish-audio
Fish Audio: Drama 3
fish-audio/drama-3
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Fish Audio's Drama 3 (fish-audio/drama-3) is a text-to-speech model listed in the OpenRouter catalog, which presents it as designed for directed voice performances. According to the catalog, users can steer delivery by placing plain-language directions in square brackets before a line of text. OpenRouter reports a Design Arena result in the audio-realism category, offering one measured signal, but no independent model card was available in this source pack, so architecture, training data, and licensing remain undocumented. Teams should validate quality on their own scripts.[1]
Strengths
- Catalog-described: accepts inline plain-language stage directions in square brackets before each line to shape vocal delivery.[1]
- Text-in, speech-out modality as listed in the OpenRouter catalog.[1]
- Has a measured evaluation entry in OpenRouter's Design Arena audio-realism category, a preference-based signal separate from vendor description.[1]
Limitations
- Catalog-only evidence: no independent model card in this source pack, so architecture, training data, language coverage, and license terms are unknown.[1]
- The catalog lists no configurable inference parameters, limiting documented tuning options.[1]
- Only one reported arena evaluation and no other quality data; suitability for a given workload requires hands-on validation.[1]
Where to use it
- Editorial suggestion: narrated audiobooks, audio drama, or scripted dialogue where per-line emotional direction could streamline production; test on representative scripts first.[1]
- Editorial suggestion: prototyping character voices for games or animation, subject to validating expressiveness and consistency.[1]
- Editorial suggestion: temporary voiceover or scratch audio for storyboards and pre-production drafts.[1]
Sources
- [1] OpenRouter catalog · Fish Audio: Drama 3Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Drama 3 is a text-to-speech model from Fish Audio built for directed voice performances. You write the direction in plain language in square brackets before a line, such as `[nervous,...
Specifications
- Model ID
- fish-audio/drama-3
- Canonical ID
- fish-audio/drama-3-20261013
- Creator
- fish-audio
- Added to OpenRouter
- 13.10.2026
- Context length
- 0
- 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
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Design Arena | models · audiorealismwin rate 34.2% · rank 4 | 958Elo | —Not rated | 13.11.2026 |
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) |
|---|---|---|---|---|---|---|
| Fish Audio | 0 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.