Fish Audio Release Notes
24 release notes curated from 1 source by the Releasebot Team. Last updated: Nov 14, 2026
- Nov 13, 2026
- Date parsed from source:Nov 13, 2026
- First seen by Releasebot:Nov 14, 2026
Swedish and Malay normalization
Fish Audio adds Swedish and Malay text normalization, with automatic Swedish detection and an option to set Malay as the text language.
Swedish and Malay normalization
Text normalization now has rules for Swedish (sv) and Malay (ms). Without language, Swedish text is detected. Malay is detected only when the detection is confident, so set language to ms for text entirely in Malay.
Supported normalization languages
Original source - Oct 29, 2026
- Date parsed from source:Oct 29, 2026
- First seen by Releasebot:Oct 29, 2026
transcribe-1 retirement
Fish Audio is retiring transcribe-1 and S1 on December 31, 2026, routing affected requests to transcribe-1-pro at the same price. Users can migrate by specifying the new model header and adjusting options for plain transcripts.
transcribe-1 retirement
transcribe-1 is deprecated and will be retired on December 31, 2026, together with S1. After that date, the requests it serves are served by transcribe-1-pro and billed as transcribe-1-pro, at the same price. This includes requests with no model header, or one that does not match exactly, and requests through the OpenAI-, Groq-, OpenRouter-, and ElevenLabs-compatible endpoints.
To migrate, send the model: transcribe-1-pro header on POST /v1/asr. For plain transcripts without speaker markers or event cues, also send diarize=false and tag_audio_events=false.
Migrate from transcribe-1 | Model deprecations
Original source All of your release notes in one feed
Join Releasebot and get updates from Fish Audio and hundreds of other software products.
- Oct 20, 2026
- Date parsed from source:Oct 20, 2026
- First seen by Releasebot:Oct 20, 2026
More normalization languages
Fish Audio expands text normalization with Turkish, Tagalog, Brazilian Portuguese, and automatic detection for Turkish, Tagalog, and Traditional Chinese.
More normalization languages
Text normalization now has rules for Turkish (tr) and Tagalog (tl, fil), and Portuguese follows Brazilian conventions, so pt-BR is supported too. Without language, Turkish and Tagalog text is detected, and Chinese written mostly in Traditional characters uses the Traditional Chinese rules.
Supported normalization languages
Original source - Oct 16, 2026
- Date parsed from source:Oct 16, 2026
- First seen by Releasebot:Oct 17, 2026
TTS language field
Fish Audio adds an optional language setting for TTS text normalization and word timestamps across API and WebSocket routes.
TTS language field
Text-to-speech requests accept an optional language field, a BCP-47 tag of the text such as en, es-MX, or zh-TW. It selects the rules used to spell out numbers, dates, units, and symbols before synthesis, and the language used for word timestamps. It does not change the voice, accent, or audio quality. Omit it to keep detecting the language per text chunk.
Available on POST /v1/tts, the with-timestamps routes, and the WebSocket start event. The official SDKs don't expose it yet.
Language | Supported normalization languages
Original source - Oct 14, 2026
- Date parsed from source:Oct 14, 2026
- First seen by Releasebot:Oct 14, 2026
Drama 3
Fish Audio releases Drama 3, a text-to-speech model directed in plain language for tone, pacing, and character, available via the API as drama-3.
Drama 3
Text-to-speech model you direct in plain language. Describe tone, pacing, and character without a fixed set of audio tags.
Use model ID drama-3 in the API.
Drama 3 guide | Text to Speech API
Original source Similar to Fish Audio with recent updates:
- Smokeball release notes149 release notes · Latest Nov 11, 2026
- Cosmolex release notes20 release notes · Latest Jul 30, 2025
- PracticePanther release notes37 release notes · Latest Oct 27, 2026
- Salesforce release notes104 release notes · Latest Nov 1, 2026
- Microsoft release notes1157 release notes · Latest Nov 17, 2026
- Zoom release notes228 release notes · Latest Nov 14, 2026
- Oct 14, 2026
- Date parsed from source:Oct 14, 2026
- First seen by Releasebot:Oct 14, 2026
Fish Audio S1 retirement
Fish Audio is retiring S1 on December 31, 2026, routing its requests to S2.1-pro at the same price and recommending tag updates.
Fish Audio S1 retirement
S1 is deprecated and will be retired on December 31, 2026. After that date, requests that specify s1 are served by s2.1-pro and billed as s2.1-pro, at the same price.
To migrate, switch the model ID to s2.1-pro and convert (parenthesis) emotion tags to [bracket] tags.
Migrate from S1 | Model deprecations
Original source - Oct 5, 2026
- Date parsed from source:Oct 5, 2026
- First seen by Releasebot:Oct 5, 2026
Drama 3 Preview
Fish Audio releases Drama 3 Preview, a text-to-speech model you can direct in plain language for tone, pacing, and character.
Drama 3 Preview
Preview text-to-speech model you direct in plain language. Describe tone, pacing, and character without a fixed set of audio tags.
Use model ID drama-3-preview in the API. Behavior and availability may change while it is in preview.
Text to Speech API
Original source - Oct 5, 2026
- Date parsed from source:Oct 5, 2026
- First seen by Releasebot:Oct 5, 2026
Transcribe 1 Pro
Fish Audio adds Transcribe 1 Pro speech-to-text for short clips, long recordings, and multi-speaker conversations with richer transcript cues.
Transcribe 1 Pro
Speech-to-text model for short clips and long recordings, including multi-speaker conversations. Transcripts can include inline speaker markers, speaker turns, and emotion and vocal-event cues.
Use model ID transcribe-1-pro on POST /v1/asr
Speech to Text | Models overview
Original source - Oct 5, 2026
- Date parsed from source:Oct 5, 2026
- First seen by Releasebot:Oct 5, 2026
Fish Audio S2.1 Pro
Fish Audio releases S2.1 Pro text-to-speech, improving quality, latency, throughput and supporting 83 languages.
Fish Audio S2.1 Pro
Production text-to-speech model that improves on S2-Pro in quality, latency, and throughput. Supports 83 languages on one model, with the same [bracket] natural-language control and multi-speaker dialogue as S2.
Use model ID s2.1-pro for production workloads that need TTFA and DPA guarantees. s2.1-pro-free is the same model at no cost through November 30, 2026 for testing, prototyping, development, and smaller businesses, under fair-use limits and without those guarantees.
Read more about S2.1 Pro | Models overview
Original source - Mar 10, 2026
- Date parsed from source:Mar 10, 2026
- First seen by Releasebot:Mar 11, 2026
- Modified by Releasebot:Oct 14, 2026
Fish Audio S2
Fish Audio releases S2, an open-source text-to-speech model with inline emotion and delivery cues, multi-speaker dialogue, and support for more than 80 languages. Existing S1 integrations remain supported, with retirement scheduled for December 31, 2026.
Fish Audio S2
Next-generation text-to-speech model with inline emotion cues, multi-speaker dialogue support, and 80+ languages.
S2 introduces [bracket] syntax for natural language control over emotion and paralinguistic cues (e.g., [whisper], [laugh], [emphasis]). Tags are treated as standard text rather than dedicated control tokens, so you are not limited to a fixed set of expressions. Built on the Qwen3-4B backbone and fully open-source.
Use model ID s2-pro in the API. At launch, S1 remained supported for existing integrations; it is now deprecated and will be retired on December 31, 2026 (see Migrate from S1).
GitHub | HuggingFace
Original source - Nov 11, 2025
- Date parsed from source:Nov 11, 2025
- First seen by Releasebot:Dec 23, 2025
Fish Audio S1
Fish Audio Overview
Historic rebrand from Fish Speech to Fish Audio. #1 ranking on TTS-Arena2 with industry-leading performance.
- S1 (4B params): 0.008 WER, 0.004 CER - Available on Fish Audio Playground
- S1-mini (0.5B params): 0.011 WER, 0.005 CER - Open source on Hugging Face
48+ emotional expressions with RLHF integration and multilingual support for English, Chinese, Japanese, and more.
Read More about S1
Original source - Nov 11, 2025
- Date parsed from source:Nov 11, 2025
- First seen by Releasebot:Dec 23, 2025
v1.5.1
Fixed critical PyTorch security settings and improved inference speed significantly. Added ONNX export support for better deployment options and enhanced text processing for Arabic and Hebrew languages. Includes bug fixes for Apple Silicon (MPS) compatibility and reorganized library structure for cleaner codebase.
Original source - Nov 11, 2025
- Date parsed from source:Nov 11, 2025
- First seen by Releasebot:Dec 23, 2025
v1.5.0
Release Notes
Introduced v1.5 model architecture with improved dataset handling and bearer token authentication for APIs.
Added reference audio caching by hash for faster performance and better Apple Silicon support. Includes OpenAPI documentation refactoring and base64 reference data support in JSON format.
- Nov 11, 2025
- Date parsed from source:Nov 11, 2025
- First seen by Releasebot:Dec 23, 2025
v1.4.2
Documentation-focused release with comprehensive updates for v1.4, macOS support, and multiple language translations.
Improved Docker support and API enhancements for JSON format handling. Added audio selection to WebUI and fixed various stability issues including cache handling and backend performance.
Original source - Nov 11, 2025
- Date parsed from source:Nov 11, 2025
- First seen by Releasebot:Dec 23, 2025
v1.2.1
Replaced Whisper with SenseVoice for better ASR and added native Apple Silicon support.
Original source
Includes Portuguese (Brazil) localization, streaming audio functionality, and CPU-only inference improvements. Pinned PyTorch to 2.3.1 to fix inference speed issues and aligned API with official closed-source version.
Curated by the Releasebot team
Releasebot is an aggregator of official release notes from hundreds of software vendors and thousands of sources.
Our editorial process involves the manual review and audit of release notes procured with the help of automated systems.