> ## Documentation Index > Fetch the complete documentation index at: https://docs.siliconflow.cn/llms.txt > Use this file to discover all available pages before exploring further. # Text to speech ## 1. Use cases ext-to-Speech (TTS) models are AI models that convert text information into spoken output. These models generate natural and expressive speech from input text, suitable for various use cases: * Providing audio readings for blog articles * Generating multilingual speech content * Supporting real-time streaming audio output ## 2. API usage guide * Endpoint: /audio/speech. For detailed usage, refer to the [API documentation](https://docs.siliconflow.cn/api-reference/audio/create-speech) * Main request parameters:： * model: The model used for speech synthesis, with a list of supported [models](/capabilities/text-to-speech#3)。 * input: The text content to be converted into audio. * voice: The reference voice, supporting [system-predefined voices](/capabilities/text-to-speech#2-1)、[user-predefined voices](/capabilities/text-to-speech#2-2)、[user-dynamic voices](/capabilities/text-to-speech#2-3). Detailed parameters: Refer to[Creating a text-to-speech request](/api-reference/audio/create-speech)。 * speed: Controls the audio speed, a float type with a default value of 1.0 and a selectable range of \[0.25, 4.0]. * gain: Audio gain in dB, controls the volume of the audio, a float type with a default value of 0.0 and a selectable range of \[-10, 10]. * response\_format: Controls the output format, supporting mp3, opus, wav, and pcm formats. Different output formats result in different sampling rates. * sample\_rate: Controls the output sampling rate, with different default values and selectable ranges depending on the output format: * opus: Currently supports only 48000 Hz. * wav, pcm: Supports (8000, 16000, 24000, 32000, 44100), default is 44100. * mp3: Supports (32000, 44100), default is 44100. Note: Do not add spaces to the input content, and the reference audio should be less than 30 seconds. ### 2.1 System-predefined voices: Currently, the system provides the following 8 voice options: * male voices: * steady male voice: [alex](https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Alex.mp3) * deep male voice: [benjamin](https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Benjamin.mp3) * magnetic male voice: [charles](https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Charles.mp3) * cheerful male voice: [david](https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-David.mp3) * female voice: * steady female voice: [anna](https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Anna.mp3) * passionate female voice: [bella](https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Bella.mp3) * gentle female voice: [claire](https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Claire.mp3) * cheerful female voice: [diana](https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Diana.mp3) [online listening](https://soundcloud.com/siliconcloud/sets/siliconcloud-online-voice)of the above audio. When using the [system-predefined voices](/capabilities/text-to-speech#5-1) in the request, you need to prepend the model name, such as: `FunAudioLLM/CosyVoice2-0.5B:alex` indicates the alex voice from the FunAudioLLM/CosyVoice2-0.5B model. ### 2.2 User-predefined voices: Note: Using user-predefined voices requires real-name authentication. To ensure the quality of the generated voice, it is recommended that users upload a voice sample that is 8 to 10 seconds long, with clear pronunciation and no background noise or interference. #### 2.2.1 Upload user-predefined voices using base64 encoding format ```python theme={null} import requests import json url = "https://api.siliconflow.cn/v1/uploads/audio/voice" headers = { "Authorization": "Bearer your-api-key", # 从 https://cloud.siliconflow.cn/account/ak 获取 "Content-Type": "application/json" } data = { "model": "FunAudioLLM/CosyVoice2-0.5B", # model name "customName": "your-voice-name", # user-predefined voices name "audio": "data:audio/mpeg;base64,SUQzBAAAAAAAIlRTU0UAAAAOAAADTGF2ZjYxLjcuMTAwAAAAAAAAAAAAAAD/40DAAAAAAAAAAAAASW5mbwAAAA8AAAAWAAAJywAfHx8fKioqKio1NTU1Pz8/Pz9KSkpKVVVVVVVfX19fampqamp1dXV1f39/f3+KioqKlZWVlZWfn5+fn6qqqqq1tbW1tb+/v7/KysrKytXV1dXf39/f3+rq6ur19fX19f////", # 参考音频的 base64 编码 "text": "在一无所知中, 梦里的一天结束了，一个新的轮回便会开始" # 参考音频的文字内容 } response = requests.post(url, headers=headers, data=json.dumps(data)) # 打印响应状态码和响应内容 print(response.status_code) print(response.json()) # 如果响应是 JSON 格式 ``` The URI field in the response is the ID of the custom voice. Users can use this ID as the voice parameter in subsequent requests. ```json theme={null} {'uri': 'speech:your-voice-name:cm04pf7az00061413w7kz5qxs:mjtkgbyuunvtybnsvbxd'} ``` In the request, use the [user-predefined](/capabilities/text-to-speech#5-2) voices as indicated. #### 2.2.2 Upload user-predefined voices through a file ```python theme={null} import requests url = "https://api.siliconflow.cn/v1/uploads/audio/voice" headers = { "Authorization": "Bearer your-api-key" # 从 https://cloud.siliconflow.cn/account/ak 获取 } files = { "file": open("/Users/senseb/Downloads/fish_audio-Alex.mp3", "rb") # 参考音频文件 } data = { "model": "FunAudioLLM/CosyVoice2-0.5B", # 模型名称 "customName": "your-voice-name", # 参考音频名称 "text": "在一无所知中, 梦里的一天结束了，一个新的轮回便会开始" # 参考音频的文字内容 } response = requests.post(url, headers=headers, files=files, data=data) print(response.status_code) print(response.json()) ``` The URI field in the response is the ID of the custom voice. Users can use this ID as the voice parameter in subsequent requests. ```json theme={null} {'uri': 'speech:your-voice-name:cm04pf7az00061413w7kz5qxs:mjtkgbyuunvtybnsvbxd'} ``` In the request, use the [user-predefined](/capabilities/text-to-speech#5-2) voices as indicated. ### 2.3 Get the list of user-dynamic voices ```python theme={null} import requests url = "https://api.siliconflow.cn/v1/audio/voice/list" headers = { "Authorization": "Bearer your-api-key" # 从https://cloud.siliconflow.cn/account/ak获取 } response = requests.get(url, headers=headers) print(response.status_code) print(response.json()) ``` The URI field in the response is the ID of the custom voice. Users can use this ID as the voice parameter in subsequent requests. ```json theme={null} {'uri': 'speech:your-voice-name:cm04pf7az00061413w7kz5qxs:mjtkgbyuunvtybnsvbxd'} ``` In the request, use the [user-predefined](/capabilities/text-to-speech#5-2) voices as indicated. ### 2.4 Use user-dynamic voices Note: Using user-predefined voices requires real-name authentication. Use the [user-dynamic](/capabilities/text-to-speech#5-3) voices in the request as indicated. ### 2.5 Delete user-dynamic voices ```python theme={null} import requests url = "https://api.siliconflow.cn/v1/audio/voice/deletions" headers = { "Authorization": "Bearer your-api-key", "Content-Type": "application/json" } payload = { "uri": "speech:your-voice-name:cm02pf7az00061413w7kz5qxs:mttkgbyuunvtybnsvbxd" } response = requests.request("POST", url, json=payload, headers=headers) print(response.status_code) print(response.text) ``` The URI field in the response is the ID of the custom voice. Users can use this ID as the voice parameter in subsequent requests. ## 3. List of supported models Note: The supported TTS models may be subject to change. Please filter by the ["Speech" tag](https://cloud.siliconflow.cn/models?types=speech) on the 「Models」to obtain the current list of supported models. Charging method: Charged based on the number of [UTF-8 bytes](https://zh.wikipedia.org/wiki/UTF-8) corresponding to the input text. [Online byte counter demo](https://mothereff.in/byte-counter). ### 3.1 FunAudioLLM/CosyVoice2-0.5B series models * Cross-Language text-to-speech: Achieve text-to-speech synthesis across different languages, including Chinese, English, Japanese, Korean, Chinese dialects (Cantonese, Sichuanese, Shanghai dialect, Zhengzhou dialect, Changsha dialect, Tianjin dialect) * Emotional control: Support the generation of speech with various emotional expressions, including happiness, excitement, sadness, anger, etc. * Fine-grained control: Control the emotional and rhythmic aspects of the generated speech through rich text or natural language. ### 3.2 fnlp/MOSS-TTSD-v0.5 * High-Expressivity Voice: Natural conversational tone with emotional expression support * Dual-Voice Cloning: Zero-shot cloning with automatic speaker switching * Bilingual Support (Chinese & English): Seamless mixed synthesis and natural pronunciation * Long-Form Speech Generation: Low-latency, stable output for lengthy texts ## 4. Best practices for reference audio Providing high-quality reference audio samples can enhance the cloning effect. ### 4.1 Audio quality guidelines * Single speaker only * Clear articulation, steady volume, tone, and emotion * Brief pauses (0.5 seconds recommended) * Ideal: No background noise, professional recording quality, no room echo * Suggested duration: 8 to 10 seconds ### 4.2 File formats * Supported formats: mp3, wav, pcm, opus * Recommend using mp3 with a bitrate above 192kbps to avoid quality loss * Additional benefits of uncompressed formats (e.g., WAV) are limited ## 5. Usage examples ### 5.1 Use system-predefined voices ```python theme={null} from pathlib import Path from openai import OpenAI speech_file_path = Path(__file__).parent / "siliconcloud-generated-speech.mp3" client = OpenAI( api_key="您的 APIKEY", # 从 https://cloud.siliconflow.cn/account/ak 获取 base_url="https://api.siliconflow.cn/v1" ) with client.audio.speech.with_streaming_response.create( model="FunAudioLLM/CosyVoice2-0.5B", # 支持 fishaudio / GPT-SoVITS / CosyVoice2-0.5B 系列模型 voice="FunAudioLLM/CosyVoice2-0.5B:alex", # 系统预置音色 # 用户输入信息 input="你能用高兴的情感说吗？<|endofprompt|>今天真是太开心了，马上要放假了！I'm so happy, Spring Festival is coming!", response_format="mp3" # 支持 mp3, wav, pcm, opus 格式 ) as response: response.stream_to_file(speech_file_path) ``` #### 5.2 Use user-predefined voices ```python theme={null} from pathlib import Path from openai import OpenAI speech_file_path = Path(__file__).parent / "siliconcloud-generated-speech.mp3" client = OpenAI( api_key="您的 APIKEY", # 从 https://cloud.siliconflow.cn/account/ak 获取 base_url="https://api.siliconflow.cn/v1" ) with client.audio.speech.with_streaming_response.create( model="FunAudioLLM/CosyVoice2-0.5B", # 支持 fishaudio / GPT-SoVITS / CosyVoice2-0.5B 系列模型 voice="speech:your-voice-name:cm02pf7az00061413w7kz5qxs:mttkgbyuunvtybnsvbxd", # 用户上传音色名称，参考 # 用户输入信息 input=" 请问你能模仿粤语的口音吗？< |endofprompt| >多保重，早休息。", response_format="mp3" ) as response: response.stream_to_file(speech_file_path) ``` #### 5.3 Use user-dynamic voices ```python theme={null} from pathlib import Path from openai import OpenAI client = OpenAI() speech_file_path = Path(__file__).parent / "siliconcloud-generated-speech.mp3" client = OpenAI( api_key="您的 APIKEY", # 从 https://cloud.siliconflow.cn/account/ak 获取 base_url="https://api.siliconflow.cn/v1" ) with client.audio.speech.with_streaming_response.create( model="FunAudioLLM/CosyVoice2-0.5B", voice="", # 此处传入空值，表示使用动态音色 # 用户输入信息 input=" [laughter]有时候，看着小孩子们的天真行为[laughter]，我们总会会心一笑。", response_format="mp3", extra_body={"references":[ { "audio": "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Alex.mp3", # 参考音频 url。也支持 base64 格式 "text": "在一无所知中, 梦里的一天结束了，一个新的轮回便会开始", # 参考音频的文字内容 } ]} ) as response: response.stream_to_file(speech_file_path) ``` #### 5.4 fnlp/MOSS-TTSD-v0.5 usage examples ```python theme={null} # -*- coding: utf-8 -*- import requests import json url = "https://api.siliconflow.cn/v1/audio/speech" token = "Your-api-key" request_data = { "model": "fnlp/MOSS-TTSD-v0.5", "stream": True, "input": "[S1]Hello, how are you today?[S2]I'm doing great, thanks for asking![S1]That's wonderful to hear.", "references": [ { "audio": "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Charles.mp3", "text": "他又躺在那里，眼睛闭着，仍然沉浸在梦境的气氛里。那是个庞杂而亮堂的梦", }, { "audio": "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Claire.mp3", "text": "他又躺在那里，眼睛闭着，仍然沉浸在梦境的气氛里。那是个庞杂而亮堂的梦" } ], "max_tokens": 1600, "response_format": "mp3", "speed": 1, "gain": 0 } headers = {'Content-Type': 'application/json', 'Authorization': "Bearer " + token} try: res = requests.post(url=url, data=json.dumps(request_data), headers=headers) if res.status_code != 200: print(res.text) with open('./test.mp3', 'wb') as file: file.write(res.content) except Exception as e: print(request_data) print(e) ```