moeru-ai/airi · error

Invalid request body

Error message

Invalid request body

What it means

The MiniMax speech (TTS) provider intercepts the SDK's speech fetch and expects the request body to be a JSON string it can parse. If init.body is missing or not a string, this error is thrown, meaning the TTS request never carried a serializable JSON payload.

Source

Thrown at packages/provider-inference/src/providers/cloud/minimax-speech/index.ts:32

  name: 'MiniMax Speech',
  nameLocalize: ({ t }) => t('settings.pages.providers.provider.minimax-speech.title'),
  description: 'minimax.io',
  descriptionLocalize: ({ t }) => t('settings.pages.providers.provider.minimax-speech.description'),
  tasks: ['text-to-speech'],
  icon: 'i-lobe-icons:minimax',
  iconColor: 'i-lobe-icons:minimax-color',
  createProviderConfig: () => minimaxSpeechConfigSchema,
  createProvider(config) {
    const apiKey = config.apiKey.trim()
    const baseUrl = (config.baseUrl || 'https://api.minimax.io').replace(/\/$/, '')

    return {
      speech: () => ({
        baseURL: `${baseUrl}/v1/`,
        model: 'speech-2.8-hd',
        fetch: async (_input: RequestInfo | URL, init?: RequestInit) => {
          if (!init?.body || typeof init.body !== 'string')
            throw new Error('Invalid request body')

          const body = JSON.parse(init.body) as { input?: string, voice?: string, model?: string }
          const response = await fetch(`${baseUrl}/v1/t2a_v2`, {
            method: 'POST',
            headers: {
              'Content-Type': 'application/json',
              'Authorization': `Bearer ${apiKey}`,
            },
            body: JSON.stringify({
              model: body.model || 'speech-2.8-hd',
              text: body.input ?? '',
              stream: true,
              voice_setting: {
                voice_id: body.voice || 'English_Graceful_Lady',
                speed: 1,
                vol: 1,
                pitch: 0,
              },

View on GitHub (pinned to f679616c34)

Solutions

1. Ensure the TTS request body is a plain JSON string containing at least 'input' (text), 'voice', and 'model'.
2. Use the provider through its SDK speech helper instead of hand-rolled fetch calls.
3. Remove middleware that converts the body to FormData or streams.
4. Pass text via the SDK option (e.g. { input: 'hello' }) so the client serializes JSON.

Example fix

// before
fetch(baseURL, { method: 'POST', body: formData })
// after
fetch(baseURL, {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({ model: 'speech-2.8-hd', input: text, voice })
})

const body = JSON.stringify({ model, input: text, voice })
if (typeof body !== 'string' || !text?.trim()) throw new TypeError('TTS request requires JSON string body with non-empty input')

const isJsonStringBody = (init?: RequestInit): init is RequestInit & { body: string } => typeof init?.body === 'string'

try { await tts(text) } catch (e) { if (e.message === 'Invalid request body') { /* send JSON.stringify'd body instead */ } else throw e }

When it happens

Trigger: Calling the speech API with a FormData/Stream/URLSearchParams body instead of JSON, or issuing a GET/empty-body request through the provider's baseURL.

Common situations: Manually calling fetch with multipart form-data; a wrapper that JSON.stringify's into an object rather than a string; using an SDK version that streams the body instead of buffering it into init.body.

Understand the failure class

Background: "Invalid ... format", "must be in format X", "does not look like a ..." — invalid argument format errors across CLI tools and libraries — this error's family across 17 libraries.

Related errors

• Invalid request body
• Invalid speech request body
• Invalid request body
• Invalid request body
• MiMo voice clone requires a base64 audio sample in data URI

AI-assisted analysis of moeru-ai/airi@f679616c34 (2026-09-08). Data as JSON: /api/errors/c04888f79ab0b714. Report an issue: GitHub.