---
type: "post"
id: "fish-audio-released-drama-3-an-open-weight-208ee1"
slug: "fish-audio-released-drama-3-an-open-weight-208ee1"
title: "Fish Audio released Drama 3 , an open-weight directable TTS model with natural-language stage directions."
description: "Drama 3 makes performance direction part of the script-to-speech interface."
retrieval_nugget: "Drama 3 makes performance direction part of the script-to-speech interface."
published_at: "2026-10-13"
updated_at: "2026-10-13"
record_date: "2026-10-13"
date_kind: "published_at"
topics: []
source_urls: ["https://fish.audio/drama-3"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:fish-audio-released-drama-3-an-open-weight-208ee1"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:cf9f754fba576a17ff033e3af46b432dcc37e453640b89147d75b72102830636","reviewed_at":"2026-10-13T20:07:20.881Z","source_evidence_count":1,"verified_claim_count":4,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":4,"implication_count":1,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Natural-language and word-scoped directions make performance control an explicit part of a TTS script, rather than a separate post-generation adjustment.","observed_facts":[{"text":"Fish Audio’s product page says users can write directions for emotion, intent, pacing, and addressee in natural language.","source_urls":["https://fish.audio/drama-3"]},{"text":"The page demonstrates sounds and pauses inline, and says effects can be limited to selected words.","source_urls":["https://fish.audio/drama-3"]},{"text":"The page says multi-speaker scripts can be generated in one pass and that Drama 3 can be called through the API using the drama-3 model header.","source_urls":["https://fish.audio/drama-3"]},{"text":"The FAQ labels the model Preview and says results vary between takes.","source_urls":["https://fish.audio/drama-3"]}],"mechanism":"Script-local directions and word-scoped tags provide controls within the text being synthesized; the API accepts the same direction format.","why_now":"Drama 3 is presented as available now in Fish Audio’s Text to Speech product and callable through its API, so the directing interface can be tried in both the editor and an integration.","implications":["For teams building voiced dialogue, direction can be authored and revised alongside the words instead of treated only as a global voice setting."],"evidence_boundary":"The supplied product page demonstrates the interface and access path, but gives no independent quality benchmark, cost comparison, or proof of open weights.","watch_conditions":["Watch whether later documentation adds reproducible quality or consistency evidence and clarifies the model’s status beyond Preview."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied; this is a distinct record on a released TTS interface that embeds performance direction in script text."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/fish-audio-released-drama-3-an-open-weight-208ee1/","markdown":"https://newruntime.com/posts/fish-audio-released-drama-3-an-open-weight-208ee1.md","json":"https://newruntime.com/posts/fish-audio-released-drama-3-an-open-weight-208ee1.json"}
---

# Fish Audio released Drama 3 , an open-weight directable TTS model with natural-language stage directions.

## Retrieval answer

Drama 3 makes performance direction part of the script-to-speech interface.

Drama 3 makes performance direction part of the script-to-speech interface. The thesis is: Natural-language and word-scoped directions make performance control an explicit part of a TTS script, rather than a separate post-generation adjustment. Fish Audio’s product page shows directions for emotion, intent, pacing, and addressee, alongside inline pauses and sounds. It also shows effects scoped to selected words, such as whispering or slower delivery.

The mechanism is: Script-local directions and word-scoped tags provide controls within the text being synthesized; the API accepts the same direction format. The page also describes multi-speaker scripts generated together and API requests using the `drama-3` model header. Why now: Drama 3 is presented as available now in Fish Audio’s Text to Speech product and callable through its API, so the directing interface can be tried in both the editor and an integration.

The first implication is: For teams building voiced dialogue, direction can be authored and revised alongside the words instead of treated only as a global voice setting. That makes script structure a practical control surface, although it does not establish consistency or production quality. The evidence boundary is: The supplied product page demonstrates the interface and access path, but gives no independent quality benchmark, cost comparison, or proof of open weights. Fish Audio says Drama 3 remains in Preview and results vary between takes. The first watch condition is: Watch whether later documentation adds reproducible quality or consistency evidence and clarifies the model’s status beyond Preview.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)