Speech Synthesis (MiMo-TTS Series) - OpenAI API Compatibility

Request Address

https://api.xiaomimimo.com/v1/chat/completions

Request Headers

The API supports the following two authentication methods. Please choose one and add it to the request headers:

api-key: $MIMO_API_KEY
Content-Type: application/json

Request body

messagesarrayRequired
The current conversation message list.
Hide child attributes
Messages sent by an end user, containing prompts or additional context information.
Note: When generating audio using the mimo-v2.5-tts-voicedesign model, this message is required and is used to specify the text describing the voice design.
Hide child attributes
messages.contentstringRequired
The contents of the user message.
messages.rolestringRequired
Role of the message author.
Available options: user
modelstringRequired
Model ID is used to generate the response.
Available options: mimo-v2.5-tts, mimo-v2.5-tts-voicedesign, mimo-v2.5-tts-voiceclone
audioobject
Parameters for audio output. For details, please refer to Speech Synthesis.
Note: To generate audio, you must add a message with role set to assistant, which needs to specify the text for speech synthesis. Additionally, when using the mimo-v2.5-tts-voicedesign model, a message with the role of user is required. If optimize_text_preview is set to true, the assistant message can be omitted.
Hide child attributes
audio.formatstringDefault: wav
Specifies the output audio format. Default: wav, or pcm when you set stream: true.
Passing in pcm or pcm16 both indicate specifying the use of the pcm16 format.
Available options: wav, mp3, pcm, pcm16
audio.optimize_text_previewbooleanDefault: false
Enables intelligent optimization of the target audio broadcast text.
When set to true, the input target text is intelligently polished; if no target text is provided, a broadcast-adapted target text is automatically generated. The finalized processed text is then fed into the model for speech synthesis.
Note: When this parameter is set to true, the assistant role message for specifying speech synthesis content can be omitted.
Currently, only the mimo-v2.5-tts-voicedesign model is supported.
audio.voicestring
The voice ID of the built-in voice or the base64 encoding of the audio sample.
mimo-v2.5-tts: This field is optional and only supports using built-in voices, with the default value being mimo_default
mimo-v2.5-tts-voiceclone: This field is required and only supports passing in the base64 encoding of audio samples, and only supports passing in audio sample files in mp3 and wav formats
mimo-v2.5-tts-voicedesign does not support this field
Available options:
mimo-v2.5-tts: mimo_default, 冰糖, 茉莉, 苏打, 白桦, Mia, Chloe, Milo, Dean
streambooleanDefault: false
If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

Chat response object (non-streaming output)

choicesarray
A list of chat completion choices.
Hide child attributes
choices.finish_reasonstring
The reason the model stopped generating tokens:
stop: The model reached a natural stop point or a user‑provided stop sequence
length: Terminated due to exceeding the model's maximum generation length
content_filter: Content was omitted due to a content filter flag
choices.indexinteger
The index of the choice in the list of choices.
choices.messageobject
A chat completion message generated by the model.
Hide child attributes
choices.message.contentstring
The contents of the message.
choices.message.rolestring
The role of the author of this message.
choices.message.audioobject
If the audio output is requested, this object contains data about the audio response from the model.
Hide child attributes
choices.message.audio.idstring
Unique identifier for this audio response.
choices.message.audio.datastring
Base64 encoded audio bytes generated by the model, in the format specified in the request.
choices.message.audio.expires_atnumber | null
The Unix timestamp (in seconds) for when this audio response expires. Currently always null.
choices.message.audio.transcriptstring | null
Transcript of the audio generated by the model. Currently always null.
choices.message.final_text_previewstring
The final audio broadcast text after intelligent optimization and polishing. This field is only returned when the request parameter optimize_text_preview is set to true.
createdinteger
The Unix timestamp (in seconds) of when the chat completion was created.
idstring
A unique identifier for the chat completion.
modelstring
The model to generate the completion.
objectstring
The object type, which is always chat.completion.
usageobject | null
Usage statistics for the completion request.
Hide child attributes
usage.completion_tokensinteger
Number of tokens in the generated completion.
usage.prompt_tokensinteger
Number of tokens in the prompt.
usage.total_tokensinteger
Total number of tokens used in the request (prompt + completion).
usage.completion_tokens_detailsobject
Breakdown of tokens used in a completion.
Hide child attributes
usage.completion_tokens_details.reasoning_tokensinteger
Tokens generated by the model for reasoning. Always 0.
usage.prompt_tokens_detailsobject
Breakdown of tokens used in the prompt.
Hide child attributes
usage.prompt_tokens_details.cached_tokensinteger
Number of tokens served from cache.

Chat response chunk object (streaming output)

choicesarray
A list of chat completion choices.
Hide child attributes
choices.deltaobject
A chat completion delta generated by streamed model responses.
Hide child attributes
choices.delta.contentstring
The contents of the chunk message.
choices.delta.rolestring
The role of the author of this message.
choices.delta.audioobject | null
If the audio output modality is requested, this object contains data about the audio response from the model.
Hide child attributes
choices.delta.audio.idstring
Unique identifier for this audio response.
choices.delta.audio.datastring
Base64 encoded audio bytes generated by the model, in the format specified in the request.
choices.delta.audio.expires_atnumber | null
The Unix timestamp (in seconds) for when this audio response expires. Currently always null.
choices.delta.audio.transcriptstring | null
Transcript of the audio generated by the model. Currently always null.
choices.delta.final_text_previewstring
The final audio broadcast text after intelligent optimization and polishing. This field is only returned when the request parameter optimize_text_preview is set to true.
choices.finish_reasonstring | null
The reason the model stopped generating tokens:
stop: The model reached a natural stop point or a user‑provided stop sequence
length: Terminated due to exceeding the model's maximum generation length
content_filter: Content was omitted due to a content filter flag
choices.indexinteger
The index of the choice in the list of choices.
createdinteger
The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp.
idstring
A unique identifier for the chat completion. Each chunk has the same ID.
modelstring
The model to generate the completion.
objectstring
The object type, which is always chat.completion.chunk.
usageobject | null
Usage statistics for the completion request.
Hide child attributes
usage.completion_tokensinteger
Number of tokens in the generated completion.
usage.prompt_tokensinteger
Number of tokens in the prompt.
usage.total_tokensinteger
Total number of tokens used in the request (prompt + completion).
usage.completion_tokens_detailsobject
Breakdown of tokens used in a completion.
Hide child attributes
usage.completion_tokens_details.reasoning_tokensinteger
Tokens generated by the model for reasoning. Always 0.
usage.prompt_tokens_detailsobject
Breakdown of tokens used in the prompt.
Hide child attributes
usage.prompt_tokens_details.cached_tokensinteger
Number of tokens served from cache.

curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts",
    "messages": [
        {
            "role": "user",
            "content": "Bright, bouncy, slightly sing-song tone — like you are bursting with good news you can barely hold in. Fast pace, rising pitch at the end."
        },
        {
            "role": "assistant",
            "content": "Hey boss — guess what, guess what? I just got the results back and I actually passed! Not just passed, I got a distinction! I know, I know — you told me I was cutting it close, but hey, here we are. Drinks are on me tonight, okay?"
        }
    ],
    "audio": {
        "format": "wav",
        "voice": "mimo_default"
    }
}'

response

{
    "id": "6ebed286b58546f6b87fa7fa9d0e806b",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "",
                "role": "assistant",
                "audio": {
                    "id": "979a91904f9a4143928d9e1f54837b4f",
                    "data": "base64Data",
                    "expires_at": null,
                    "transcript": null
                },
                "tool_calls": null
            }
        }
    ],
    "created": 1776954802,
    "model": "mimo-v2.5-tts",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 97,
        "prompt_tokens": 213,
        "total_tokens": 310,
        "completion_tokens_details": {
            "reasoning_tokens": 0
        },
        "prompt_tokens_details": {
            "cached_tokens": 109
        }
    }
}

Update Time July 17, 2026

curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts",
    "messages": [
        {
            "role": "user",
            "content": "Bright, bouncy, slightly sing-song tone — like you are bursting with good news you can barely hold in. Fast pace, rising pitch at the end."
        },
        {
            "role": "assistant",
            "content": "Hey boss — guess what, guess what? I just got the results back and I actually passed! Not just passed, I got a distinction! I know, I know — you told me I was cutting it close, but hey, here we are. Drinks are on me tonight, okay?"
        }
    ],
    "audio": {
        "format": "wav",
        "voice": "mimo_default"
    }
}'

response

{
    "id": "6ebed286b58546f6b87fa7fa9d0e806b",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "",
                "role": "assistant",
                "audio": {
                    "id": "979a91904f9a4143928d9e1f54837b4f",
                    "data": "base64Data",
                    "expires_at": null,
                    "transcript": null
                },
                "tool_calls": null
            }
        }
    ],
    "created": 1776954802,
    "model": "mimo-v2.5-tts",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 97,
        "prompt_tokens": 213,
        "total_tokens": 310,
        "completion_tokens_details": {
            "reasoning_tokens": 0
        },
        "prompt_tokens_details": {
            "cached_tokens": 109
        }
    }
}