> ## Documentation Index
> Fetch the complete documentation index at: https://docs.jiekou.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini 2.5 Flash TTS Text-to-Speech

Convert text to speech based on the Vertex AI generateContent API. The request body format is fully consistent with the official Vertex AI API. Both synchronous (single request, single response) and streaming (single request, streaming response) modes are supported. The output is in LINEAR16 PCM format (24kHz, mono, 16-bit signed little-endian) and does not include a WAV header.

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum value: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="contents" type="object" required={true}>
  <Expandable title="properties" defaultOpen={true}>
    <ParamField body="role" type="string" required={true} default="user">
      Role, fixed as user

      Allowed value: `user`
    </ParamField>

    <ParamField body="parts" type="object" required={true}>
      <Expandable title="properties" defaultOpen={true}>
        <ParamField body="text" type="string" required={true}>
          The text content to synthesize into speech. The Vertex AI API combines the prompt and text into a single field in the format '{prompt}: {text}', for example 'Say the following in a curious way: OK, so... tell me about this AI thing.'. The total size can be up to 8000 bytes, and audio exceeding 655 seconds will be truncated. Inline marker tags are supported: \[sigh], \[laughing], \[uhm], \[sarcasm], \[robotic], \[shouting], \[whispering], \[extremely fast], \[short pause], \[medium pause], \[long pause]

          Length limit: 0 - 8000
        </ParamField>
      </Expandable>
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="generation_config" type="object" required={true}>
  <Expandable title="properties" defaultOpen={true}>
    <ParamField body="temperature" type="number" default={2}>
      Temperature parameter, controlling the randomness and creativity of speech generation. Higher values produce more creative and diverse results, while lower values are more predictable and focused. Valid range: (0.0, 2.0], recommended value: 2.0

      Value range: \[0, 2]
    </ParamField>

    <ParamField body="speech_config" type="object" required={true}>
      <Expandable title="properties" defaultOpen={true}>
        <ParamField body="voice_config" type="object">
          Single-speaker voice configuration. Choose either this or multi\_speaker\_voice\_config

          <Expandable title="properties" defaultOpen={true}>
            <ParamField body="prebuilt_voice_config" type="object">
              <Expandable title="properties" defaultOpen={true}>
                <ParamField body="voice_name" type="string">
                  Prebuilt voice name (case-insensitive). 30 available voices (both male and female voices are available)

                  Allowed values: `Achernar`, `Achird`, `Algenib`, `Algieba`, `Alnilam`, `Aoede`, `Autonoe`, `Callirrhoe`, `Charon`, `Despina`, `Enceladus`, `Erinome`, `Fenrir`, `Gacrux`, `Iapetus`, `Kore`, `Laomedeia`, `Leda`, `Orus`, `Pulcherrima`, `Puck`, `Rasalgethi`, `Sadachbia`, `Sadaltager`, `Schedar`, `Sulafat`, `Umbriel`, `Vindemiatrix`, `Zephyr`, `Zubenelgenubi`
                </ParamField>
              </Expandable>
            </ParamField>
          </Expandable>
        </ParamField>

        <ParamField body="language_code" type="string" required={true}>
          Language code (BCP-47 format, case-insensitive). GA languages: ar-EG, bn-BD, nl-NL, en-IN, en-US, fr-FR, de-DE, hi-IN, id-ID, it-IT, ja-JP, ko-KR, mr-IN, pl-PL, pt-BR, ro-RO, ru-RU, es-ES, ta-IN, te-IN, th-TH, tr-TR, uk-UA, vi-VN. Preview languages include cmn-CN (Mandarin Chinese) and 63 others

          Allowed values: `af-ZA`, `am-ET`, `ar-001`, `ar-EG`, `az-AZ`, `be-BY`, `bg-BG`, `bn-BD`, `ca-ES`, `ceb-PH`, `cmn-CN`, `cmn-TW`, `cs-CZ`, `da-DK`, `de-DE`, `el-GR`, `en-AU`, `en-GB`, `en-IN`, `en-US`, `es-419`, `es-ES`, `es-MX`, `et-EE`, `eu-ES`, `fa-IR`, `fi-FI`, `fil-PH`, `fr-CA`, `fr-FR`, `gl-ES`, `gu-IN`, `he-IL`, `hi-IN`, `hr-HR`, `ht-HT`, `hu-HU`, `hy-AM`, `id-ID`, `is-IS`, `it-IT`, `ja-JP`, `jv-JV`, `ka-GE`, `kn-IN`, `ko-KR`, `kok-IN`, `la-VA`, `lb-LU`, `lo-LA`, `lt-LT`, `lv-LV`, `mai-IN`, `mg-MG`, `mk-MK`, `ml-IN`, `mn-MN`, `mr-IN`, `ms-MY`, `my-MM`, `nb-NO`, `ne-NP`, `nl-NL`, `nn-NO`, `or-IN`, `pa-IN`, `pl-PL`, `ps-AF`, `pt-BR`, `pt-PT`, `ro-RO`, `ru-RU`, `sd-IN`, `si-LK`, `sk-SK`, `sl-SI`, `sq-AL`, `sr-RS`, `sv-SE`, `sw-KE`, `ta-IN`, `te-IN`, `th-TH`, `tr-TR`, `uk-UA`, `ur-PK`, `vi-VN`
        </ParamField>

        <ParamField body="multi_speaker_voice_config" type="object">
          Multi-speaker voice configuration. Choose either this or voice\_config. Note: gemini-2.5-flash-lite-preview-tts does not support multi-speaker synthesis

          <Expandable title="properties" defaultOpen={true}>
            <ParamField body="speaker_voice_configs" type="object[]">
              List of speaker voice configurations

              <Expandable title="properties" defaultOpen={true}>
                <ParamField body="speaker" type="string" required={true}>
                  Speaker alias, which must consist only of alphanumeric characters and contain no spaces. It must match the speaker identifier in contents.parts.text
                </ParamField>

                <ParamField body="voice_config" type="object" required={true}>
                  <Expandable title="properties" defaultOpen={true}>
                    <ParamField body="prebuilt_voice_config" type="object">
                      <Expandable title="properties" defaultOpen={true}>
                        <ParamField body="voice_name" type="string">
                          Prebuilt voice name (case-insensitive). 30 available voices (both male and female voices are available)

                          Allowed values: `Achernar`, `Achird`, `Algenib`, `Algieba`, `Alnilam`, `Aoede`, `Autonoe`, `Callirrhoe`, `Charon`, `Despina`, `Enceladus`, `Erinome`, `Fenrir`, `Gacrux`, `Iapetus`, `Kore`, `Laomedeia`, `Leda`, `Orus`, `Pulcherrima`, `Puck`, `Rasalgethi`, `Sadachbia`, `Sadaltager`, `Schedar`, `Sulafat`, `Umbriel`, `Vindemiatrix`, `Zephyr`, `Zubenelgenubi`
                        </ParamField>
                      </Expandable>
                    </ParamField>
                  </Expandable>
                </ParamField>
              </Expandable>
            </ParamField>
          </Expandable>
        </ParamField>
      </Expandable>
    </ParamField>
  </Expandable>
</ParamField>

## Response Information

<ResponseField name="audioContent" type="string" required={false}>
  Base64-encoded audio content. The format is LINEAR16 PCM (24kHz, mono, 16-bit signed little-endian) and does not include a WAV header. The client can use ffmpeg to convert it: ffmpeg -f s16le -ar 24k -ac 1 -i input.raw output.wav
</ResponseField>

<ResponseField name="usageMetadata" type="object" required={false}>
  <Expandable title="properties" defaultOpen={true}>
    <ResponseField name="totalTokenCount" type="integer" required={false}>
      Total number of tokens (promptTokenCount + candidatesTokenCount)
    </ResponseField>

    <ResponseField name="promptTokenCount" type="integer" required={false}>
      Number of tokens consumed by the input text
    </ResponseField>

    <ResponseField name="candidatesTokenCount" type="integer" required={false}>
      Number of tokens consumed by the output audio (approximately 25 tokens per second of audio)
    </ResponseField>
  </Expandable>
</ResponseField>