fishaudio · leng-yue · Jul 14, 2026
diff --git a/.mintlify/skills/fish-audio-sdk/references/text-to-speech.md b/.mintlify/skills/fish-audio-sdk/references/text-to-speech.md
@@ -17,7 +17,7 @@ save(audio, "out.mp3")
 # Use a specific voice model by id
 audio = client.tts.convert(
     text="Using a saved voice.",
-    reference_id="802e3bc2b27e49c2995d23ef70e6ac89",
+    reference_id="9a9cf47702da476aa4629e2506d4a857",
 )
 
 # Pick a model and adjust speed
@@ -95,7 +95,7 @@ await play(audio);
 const audio2 = await client.textToSpeech.convert(
   {
     text: "Using a saved voice.",
-    reference_id: "802e3bc2b27e49c2995d23ef70e6ac89",
+    reference_id: "9a9cf47702da476aa4629e2506d4a857",
   },
   "s1" // <-- positional backend, not { backend: "s1" }
 );

diff --git a/api-reference/asyncapi.yml b/api-reference/asyncapi.yml
@@ -144,7 +144,7 @@ components:
               text: ""
               format: mp3
               chunk_length: 300
-              reference_id: "802e3bc2b27e49c2995d23ef70e6ac89"
+              reference_id: "9a9cf47702da476aa4629e2506d4a857"
               latency: normal
         - name: Full Configuration with All Options
           payload:
@@ -165,7 +165,7 @@ components:
               mp3_bitrate: 128
               opus_bitrate: -1000
               references: []
-              reference_id: "802e3bc2b27e49c2995d23ef70e6ac89"
+              reference_id: "9a9cf47702da476aa4629e2506d4a857"
               latency: normal
               prosody:
                 speed: 1.2

diff --git a/api-reference/sdk/python/overview.mdx b/api-reference/sdk/python/overview.mdx
@@ -11,7 +11,7 @@
 [![PyPI version](https://img.shields.io/pypi/v/fish-audio-sdk.svg)](https://badge.fury.io/py/fish-audio-sdk)
 [![Python Version](https://img.shields.io/badge/python-3.9+-blue)](https://pypi.org/project/fish-audio-sdk/)
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/fish-audio-sdk)](https://pypi.org/project/fish-audio-sdk/)
 [![codecov](https://img.shields.io/codecov/c/github/fishaudio/fish-audio-python)](https://codecov.io/gh/fishaudio/fish-audio-python)
 [![License](https://img.shields.io/github/license/fishaudio/fish-audio-python)](https://github.com/fishaudio/fish-audio-python/blob/main/LICENSE)

 The official Python library for the Fish Audio API
@@ -97,7 +97,7 @@
 # Use a specific voice by ID
 audio = client.tts.convert(
     text="Custom voice",
-    reference_id="802e3bc2b27e49c2995d23ef70e6ac89"
+    reference_id="9a9cf47702da476aa4629e2506d4a857"
 )
 ```
 

diff --git a/api-reference/sdk/python/types.mdx b/api-reference/sdk/python/types.mdx
@@ -51,8 +51,8 @@

 **Attributes**:

 - `id` - Unique voice model identifier (use as reference_id in TTS)
 - `type` - Model type. Options: "svc" (singing voice conversion), "tts" (text-to-speech)
 - `title` - Voice model title/name
 - `description` - Detailed description of the voice model
 - `cover_image` - URL to the voice model's cover image
@@ -62,8 +62,8 @@
 - `samples` - List of audio samples demonstrating the voice
 - `created_at` - Timestamp when the model was created
 - `updated_at` - Timestamp when the model was last updated
 - `languages` - List of supported language codes (e.g., ["en", "zh"])
 - `visibility` - Model visibility. Options: "public", "private", "unlist"
 - `lock_visibility` - Whether visibility setting is locked
 - `like_count` - Number of likes the model has received
 - `mark_count` - Number of bookmarks/favorites
@@ -165,7 +165,7 @@

 ```python
 @classmethod
 def from_speed_override(cls,
                        speed: float,
                        base: Optional["Prosody"] = None) -> "Prosody"
 ```
@@ -184,7 +184,7 @@

 <a id="fishaudio.types.tts.TTSConfig"></a>

 ## TTSConfig Objects

 ```python
 class TTSConfig(BaseModel)
@@ -197,15 +197,15 @@

 **Attributes**:

 - `format` - Audio output format. Options: "mp3", "wav", "pcm", "opus". Default: "mp3"
 - `sample_rate` - Audio sample rate in Hz. If None, uses format-specific default.
 - `mp3_bitrate` - MP3 bitrate in kbps. Options: 64, 128, 192. Default: 128
 - `opus_bitrate` - Opus bitrate in kbps. Options: -1000, 24, 32, 48, 64. Default: 32
 - `normalize` - Whether to normalize/clean the input text. Default: True
 - `chunk_length` - Characters per generation chunk. Range: 100-300. Default: 200.
   Lower values = faster initial response, higher values = better quality
 - `latency` - Generation mode. Options: "normal" (higher quality), "balanced" (faster). Default: "balanced"
-- `reference_id` - Voice model ID from fish.audio (e.g., "802e3bc2b27e49c2995d23ef70e6ac89").
+- `reference_id` - Voice model ID from fish.audio (e.g., "9a9cf47702da476aa4629e2506d4a857").
   Find IDs in voice URLs or via voices.list()
 - `references` - List of reference audio samples for instant voice cloning. Default: []
 - `prosody` - Speech speed and volume settings. Default: None (uses natural prosody)
@@ -220,7 +220,7 @@

 <a id="fishaudio.types.tts.TTSRequest"></a>

 ## TTSRequest Objects

 ```python
 class TTSRequest(BaseModel)
@@ -235,10 +235,10 @@

 - `text` - Text to synthesize into speech
 - `chunk_length` - Characters per generation chunk. Range: 100-300. Default: 200
 - `format` - Audio output format. Options: "mp3", "wav", "pcm", "opus". Default: "mp3"
 - `sample_rate` - Audio sample rate in Hz. If None, uses format-specific default
 - `mp3_bitrate` - MP3 bitrate in kbps. Options: 64, 128, 192. Default: 128
 - `opus_bitrate` - Opus bitrate in kbps. Options: -1000, 24, 32, 48, 64. Default: 32
 - `references` - List of reference audio samples for voice cloning. Default: []
 - `reference_id` - Voice model ID for using a specific voice. Default: None
 - `normalize` - Whether to normalize/clean the input text. Default: True
@@ -338,7 +338,7 @@
 #### warn\_if\_deprecated\_model

 ```python
 def warn_if_deprecated_model(model: str) -> None
 ```

 Emit a deprecation warning if a legacy model is used.
@@ -351,7 +351,7 @@

 <a id="fishaudio.types.asr.ASRSegment"></a>

 ## ASRSegment Objects

 ```python
 class ASRSegment(BaseModel)
@@ -367,7 +367,7 @@

 <a id="fishaudio.types.asr.ASRResponse"></a>

 ## ASRResponse Objects

 ```python
 class ASRResponse(BaseModel)

diff --git a/archive/python-sdk-legacy/text-to-speech.mdx b/archive/python-sdk-legacy/text-to-speech.mdx
@@ -57,8 +57,8 @@
 
 The `reference_id` is the model ID from the URL when viewing a model on Fish Audio:
 
-- Model URL: `https://fish.audio/m/802e3bc2b27e49c2995d23ef70e6ac89`
-- Reference ID: `802e3bc2b27e49c2995d23ef70e6ac89`
+- Model URL: `https://fish.audio/m/9a9cf47702da476aa4629e2506d4a857`
+- Reference ID: `9a9cf47702da476aa4629e2506d4a857`
 
 You can also get model IDs programmatically:
 
@@ -89,7 +89,7 @@

 Common emotions: `(happy)`, `(sad)`, `(angry)`, `(excited)`, `(calm)`, `(surprised)`, `(whispering)`, `(shouting)`, `(laughing)`, `(sighing)`

 For more advanced control over speech generation, including phoneme-level control and additional paralanguage features, see [Fine-grained Control](/developer-guide/core-features/fine-grained-control).

 ## Audio Formats

@@ -209,7 +209,7 @@

 ## Next Steps

 - [Fine-grained control](/developer-guide/core-features/fine-grained-control) for phoneme-level control and paralanguage
 - [Voice cloning](/features/voice-cloning) for custom voices
 - [WebSocket streaming](/features/realtime-streaming) for real-time apps
 - [Guide and Best Practices](/features/text-to-speech) for production use

diff --git a/developer-guide/getting-started/quickstart.mdx b/developer-guide/getting-started/quickstart.mdx
@@ -209,10 +209,10 @@ Choose a voice to try:
   </Tab>
 
   <Tab title="Energetic Male">
-    From: https://fish.audio/m/802e3bc2b27e49c2995d23ef70e6ac89
+    From: https://fish.audio/m/9a9cf47702da476aa4629e2506d4a857
 
     ```bash
-    export REFERENCE_ID="802e3bc2b27e49c2995d23ef70e6ac89"
+    export REFERENCE_ID="9a9cf47702da476aa4629e2506d4a857"
     ```
   </Tab>
 </Tabs>

diff --git a/features/text-to-speech.mdx b/features/text-to-speech.mdx
@@ -23,7 +23,7 @@

 <CardGroup cols={2}>
  <Card title="Voiceovers & narration" icon="film">
    Audiobooks, explainers, ads, and video narration.
  </Card>
  <Card title="Conversational AI" icon="comments">
    Speak an assistant's replies — pair with [streaming](/features/realtime-streaming) for low latency.
@@ -42,7 +42,7 @@

 <CodeGroup>
 ```python Python
 from fishaudio import FishAudio
 from fishaudio.utils import save

 client = FishAudio()  # reads FISH_API_KEY
@@ -85,7 +85,7 @@
 ```python Python
 audio = client.tts.convert(
     text="This uses a specific voice.",
-    reference_id="802e3bc2b27e49c2995d23ef70e6ac89",
+    reference_id="9a9cf47702da476aa4629e2506d4a857",
 )
 ```
 
@@ -96,7 +96,7 @@
   --header "model: s2-pro" \
   --data '{
     "text": "This uses a specific voice.",
-    "reference_id": "802e3bc2b27e49c2995d23ef70e6ac89",
+    "reference_id": "9a9cf47702da476aa4629e2506d4a857",
     "format": "mp3"
   }' \
   --output out.mp3
@@ -193,16 +193,16 @@

 To reuse a voice across many requests, [clone it once](/features/voice-cloning) and pass the resulting `reference_id` instead.

 ### Format & bitrate

 Pick a format for your delivery channel, and tune bitrate to trade size against quality:

 | Format | Notes |
 |---|---|
 | `mp3` (default) | good size/quality balance; set `mp3_bitrate` to `64`, `128`, or `192` |
 | `wav` | uncompressed, highest quality; set `sample_rate` (e.g. `44100`) |
 | `pcm` | raw samples, no container — for low-latency playback and telephony pipelines |
 | `opus` | efficient for streaming; bitrate is automatic (`opus_bitrate=-1000`) |

 ```python
 from fishaudio.types import TTSConfig

diff --git a/snippets/audio-transcript.jsx b/snippets/audio-transcript.jsx
@@ -9,7 +9,7 @@ export const AudioTranscript = ({ voices, page }) => {
         const baseUrl = 'https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio';
         const pageVoices = [
           { id: 'ca3007f96ae7499ab87d27ea3599956a', name: 'E-girl' },
-          { id: '802e3bc2b27e49c2995d23ef70e6ac89', name: 'Energetic Male' },
+          { id: '9a9cf47702da476aa4629e2506d4a857', name: 'Energetic Male' },
           { id: '933563129e564b19a115bedd57b7406a', name: 'Sarah' },
           { id: 'bf322df2096a46f18c579d0baa36f41d', name: 'Adrian' },
           { id: 'b347db033a6549378b48d00acb0d06cd', name: 'Selene' },

diff --git a/speaker-config.yaml b/speaker-config.yaml
@@ -6,7 +6,7 @@
 # Voice Configuration (map of voice ID -> display name)
 voices:
   ca3007f96ae7499ab87d27ea3599956a: E-girl
-  802e3bc2b27e49c2995d23ef70e6ac89: Energetic Male
+  9a9cf47702da476aa4629e2506d4a857: Energetic Male
   933563129e564b19a115bedd57b7406a: Sarah
   bf322df2096a46f18c579d0baa36f41d: Adrian
   b347db033a6549378b48d00acb0d06cd: Selene

diff --git a/tests/cookbooks/harness.py b/tests/cookbooks/harness.py
@@ -15,7 +15,7 @@
 
 BASE_URL = "https://api.fish.audio"
 # Validated public voice ("Energetic Male"), used to fill <voice-id> placeholders.
-PUBLIC_VOICE = "802e3bc2b27e49c2995d23ef70e6ac89"
+PUBLIC_VOICE = "9a9cf47702da476aa4629e2506d4a857"
 _WORKSPACE_ENV = "/Users/shawnlai/project/fish-audio/.env"
 _LOCAL_KEYFILE = "/tmp/claude/fishdoctest/fishkey"
 

diff --git a/tests/js/run.mjs b/tests/js/run.mjs
@@ -14,7 +14,7 @@ import { SPECS } from "./specs.mjs";
 const HERE = dirname(fileURLToPath(import.meta.url));
 const FISH = resolve(HERE, "../..");
 const WS = resolve(FISH, "..");
-const PUBLIC_VOICE = "802e3bc2b27e49c2995d23ef70e6ac89";
+const PUBLIC_VOICE = "9a9cf47702da476aa4629e2506d4a857";
 
 function resolveKey() {
   if (process.env.FISH_API_KEY) return process.env.FISH_API_KEY.trim();