Fish Audio S1 is a text-to-speech model suited to courses, chapter narration, and continuously updated explainer content. The platform guide positions it as a stability-focused choice, especially for production workflows that prioritize making long text flow smoothly before adjusting voice tone and pacing. After specifying model: s1, you can reuse an existing voice or synthesize speech with a reference recording, then deliver the result through an audio link.
Clarify the model, inputs and outputs, and invocation method before selecting.
Capability descriptions are based on public model materials and this platform's documentation; actual parameters, outputs, and billing rules are subject to the relevant API and pricing sections.
Learn about the voice tasks s1 is suited to solving.
Course and long-form voiceovers need to consistently preserve sentence relationships and vocal character. The platform guide recommends comparing S1 for tasks that prioritize long-text stability; during production, you should still split content by chapter and review proper nouns and numbers, rather than treating the model's positioning as a guarantee that every output will be error-free.
Reuse a saved voice through reference_id so openings, body text, and supplementary content in the same series retain a consistent vocal character. Voice references and model selection are configured separately, making this suitable for content projects with a fixed narrator or brand voice.
You can choose MP3 delivery or use a WAV container for mixing and editing workflows. prosody controls speech rate and volume, making it easy to first generate a short sample, establish the pacing, and then produce subsequent chapters with the same settings.
Choose based on specific content and delivery method.
Split teaching scripts into sections by topic, and preprocess abbreviations, formulas, and technical names. Use the same voice and speaking rate to generate each section, then complete course production with subtitles and visuals after review.
Store scripts, models, and voice information by chapter. When pronunciation or pause issues are found, redo only the sections that need revision, reducing rework for the entire piece while maintaining the editing pace.
Convert product tutorials, operating instructions, and help copy into a consistent voice. Keep version records for added or revised text to make it easy to recreate corresponding prompts after product updates.
Compare based on scripts, voice, and production cost.
If the task places greater emphasis on chapter continuity and repeatable editing, start by previewing S1. For short content with stronger expressiveness, also compare S2 Pro; upgraded models do not replace evaluation using actual scripts.
The platform default model is s2-pro; using S1 requires setting the model request header. Saving the model, voice, format, and script version helps reproduce the production settings for a batch of content.
Preview first, then expand to formal content.
Define the reading purpose, proofread the script, and choose a saved voice or prepare a reference recording and transcript.
Explicitly specify s1, and use a representative passage to confirm pronunciation, rhythm, and output format.
Save settings and task IDs, obtain the audio link after completion, then arrange playback, editing, or content delivery.
Understand the synthesis method and delivery scope.
Answers to common questions about using s1.
The platform guide recommends S1 as a choice focused on long-text stability, suitable for content where clear narration is the priority. Actual performance depends on the script, voice reference, and generation settings, so you should first listen to representative passages.
Specify s1 through the HTTP request header model. If unspecified, the default is s2-pro; the voice reference_id is used for voice selection and is configured separately from the synthesis model.
For fixed characters or serialized content, use reference_id to reuse a voice; for one-time projects, use references to provide recordings and transcripts. The two are mutually exclusive, and one-time cloning accepts only one reference sample.
prosody.speed=1.0 indicates the original speed, and volume uses dB, with 0 meaning no change in volume. You can choose mp3, wav, or pcm; the latter two both use the WAV container, and MP3 bitrates can be 64, 128, or 192.
After setting callback_url, first save task_id and started_at, then wait for the completion callback; you can also query by task ID. Only after obtaining audio_url can you proceed to playback or editing.
Model information · Updated: 2026-10-01. For call parameters and billing rules, see the API and pricing sections.
Start with representative scripts and determine whether it is suitable through listening tests and actual delivery.
This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs