Errors
Configuration errors
Configuration errors indicate that something about the API call was not configured correctly. The error message you get from the Hume APIs will often contain more information than we’re able to provide on this page. For example if an audio file is too long, the error message from the API will specify the limit as well as the length of the audio received.
| Code | Description |
|---|---|
| E0100 | The WebSocket request could not be parsed as valid JSON. The Hume API requires JSON serializable payloads. |
| E0101 | You may be missing or improperly formatting a required field. This generic error indicates that the structure of your WebSocket request was invalid. Please see the error message you received in the API response for more details. |
| E0102 | The requested model was incompatible with the file format received. Some models are not compatible with every file type. For example, no facial expressions will be detected in a text file. Audio can be extracted out of some video files, but if the video has no audio, then models like Speech Prosody and Vocal Burst will not be available. |
| E0200 | Media provided could not be parsed into a known file format. Hume APIs support a wide range of file formats and media types including audio, video, image, text, but not all formats are supported. If you receive this error and believe your file type should be supported please reach out to our support team. |
| E0201 | Media could not be decoded as a base64 encoded string. The data field in the request payload should be base64 encoded bytes. If you want to pass raw text without encoding it you can do so with the raw_text parameter. |
| E0202 | No audio signal could be inferred from the media provided. This error indicates that audio models were configured, but the media provided could not be parsed into a valid audio file. |
| E0203 | Your audio file was too long. The limit is 5000 milliseconds. The WebSocket endpoints are intended for near real-time processing of data streams. For larger files, consider using the Hume Expression Measurement API REST endpoints. |
| E0204 | Your video file was too long. The limit is 5000 milliseconds. For best performance we recommend passing individual frames of video as images rather than full video files. For larger files, consider using the Hume Expression Measurement API REST endpoints. |
| E0205 | Your image file was too large. The limit is 3,000 x 3,000 pixels. The WebSocket endpoints are intended for near real-time processing of data streams. For larger files, consider using the Hume Expression Measurement API REST endpoints. |
| E0206 | Your text file was too long. The limit is 10,000 characters. The WebSocket endpoints are intended for near real-time processing of data streams. For larger files, consider using the Hume Expression Measurement API REST endpoints. |
| E0207 | The URL you’ve provided appears to be incorrect. Please verify that you’ve entered the correct URL and try submitting it again. If you’re copying and pasting, ensure that the entire URL has been copied without any missing characters. |
| E0300 | You’ve run out of credits. Activate billing to continue making API calls. |
| E0301 | Your monthly credit limit has been reached. Once billing is activated, users can accrue charges up to a predetermined monthly cap. This limit ensures that users do not accumulate excessive debt without assurance of payment. If you require a higher limit, you may manually apply for a credit limit increase on the Usage page. Alternatively, the limit will reset at the beginning of the next month. For more information, please see our docs on billing. |
| E0400 | You’ve referenced a resource that doesn’t exist in our system. Please check if the name or identifier you used is correct and try again. |
| E0401 | Your upload failed. Please ensure your file meets our format and size requirements, and attempt to upload it again. |
| E0600 | The requested resource could not be found. Please check the resource identifier and try again. |
| E0601 | The request timed out while waiting for a response. Please try again later. |
| E0602 | You do not have permission to access the requested resource. Please verify your credentials and resource ownership. |
| E0603 | The request payload was malformed. Please check the structure of your request and try again. |
| E0700 | You have too many active chats associated with your Hume account. Please close an existing chat session before starting a new one. The error message will specify your current active count and limit. |
| E0701 | The API key provided for the supplemental language model is not valid. Please verify your API key and try again. |
| E0702 | A function call to a tool returned an error. Please check your tool schema and function call handler for issues. |
| E0703 | The EVI configuration is invalid. The error message will contain specific details about what is misconfigured. Please review your configuration and try again. |
| E0704 | Audio settings cannot be changed after audio data has already been received. Please configure audio settings before sending any audio data. |
| E0705 | Your custom model was disconnected due to a server connection interruption. Please check your internet connection, ensure the server is still running, and verify that the server URL is correct. Also, make sure no firewall or security settings are blocking the connection. |
| E0706 | Hume’s API cannot reach your custom language model. Please ensure that your language model is accessible and try again. |
| E0707 | The message sent to Hume is not formed in the correct way of either {"type": "assistant_input", "text": <your text here>} or {"type": "assistant_end"} |
| E0708 | The chat group you’re trying to resume does not exist. Please check the chat group identifier and try again. |
| E0709 | The configuration you are trying to use does not exist. Please check the configuration identifier and try again. |
| E0711 | You are attempting to use a supplemental language model that is not currently available as a Hume-managed LLM. Please provide an API key from your model provider, or switch to a different supplemental LLM. |
| E0712 | The custom language model timed out during the connection attempt. This could be due to network issues, server availability, or firewall restrictions. Please check your connection and try again. |
| E0713 | The connection failed to the custom model due to a fatal error during the connection attempt. Please verify that the custom language model is correctly configured and accessible. |
| E0714 | The EVI WebSocket connection was closed due to the user inactivity timeout being reached. This timeout is specified in the inactivity parameter within the timeouts field of your EVI configuration. |
| E0715 | The EVI WebSocket connection was closed due to the maximum duration timeout being reached. This timeout is specified in the max_duration parameter within the timeouts field of your EVI configuration. |
| E0716 | The session settings provided were invalid and therefore were not applied. More details about how to resolve the misconfiguration are available in the API response. |
| E0717 | The EVI WebSocket connection was closed because a request was made to resume a chat group which contains an active chat. Please check that you are not already running an active chat session with the same chat group. |
| E0718 | The supplemental LLM provider has degraded API behavior. You can try again later or change the supplemental LLM in your EVI configuration. |
| E0719 | The supplemental LLM provider has an outage. You can try again later or change the supplemental LLM in your EVI configuration. |
| E0720 | The chat group configured for chat resumability could not be found. Please check that you specified your resumed_chat_group_id parameter correctly and that data retention is enabled in your account settings. |
| E0721 | The chat was ended due to a content safety violation. Please review the content being sent and ensure it complies with our Acceptable Use Policy. |
| E0722 | The dynamic variables template is invalid. Please check your template syntax and ensure all variables are properly formatted. Variables will not be injected if the template cannot be parsed. |
| E0723 | Failed to parse incoming audio. Data was formatted as whole audio files. Audio must be streamed. Please visit https://dev.hume.ai/reference/speech-to-speech-evi/chat#send.AudioInput.data for more information on audio guidelines. |
| E0724 | The custom language model endpoint returned an error. Please check that your custom language model is functioning correctly and returning valid responses. |
| E0725 | The audio encoding provided is not supported. Currently, linear16 is the only supported raw encoding. Please convert your audio to a supported encoding and try again. |
| E0726 | The EVI version specified in your configuration has been deprecated. Please update your EVI configuration to use a supported version. |
| E0727 | Unable to execute the requested short response system prompt operation. Please check the error message for details. |
| E0728 | Invalid audio configuration query parameters. When specifying audio settings on the WebSocket handshake, all three parameters (audio_encoding, audio_channels, audio_sample_rate) must be provided together, or none of them. |
| E0729 | The specified Chat ID does not exist, has already ended, or you do not have access to it. |
| E0730 | The specified Chat ID does not allow additional connections. Ensure the chat was started with the allow_connection=True query parameter to enable listening. |
The connection will be closed automatically after ten identical configuration errors to avoid unintended looping.
TTS errors
Text-to-speech (TTS) errors occur when using the Octave TTS API. These errors indicate issues with voice generation, voice cloning, or content policy violations.
| Code | Description |
|---|---|
| E0800 | The num_generations value provided is not supported. Please check the error message for supported values. |
| E0801 | The request may violate our Acceptable Use Policy. Please modify the content of your request and try again. |
| E0802 | Unable to randomize the requested voice parameter. Please try again. |
| E0803 | Voice cloning from a file is not enabled for your account. Please upgrade your plan or contact support. |
| E0804 | One of the utterances in your request contains invalid text. The error message will indicate which utterance index is affected. |
| E0805 | Unable to enhance the provided text. Please try again or simplify the text input. |
| E0806 | No speech was detected in the audio sample provided for voice cloning. Please ensure your audio sample contains clear speech. |
| E0807 | The audio sample provided for voice cloning is too short. The error message will specify the minimum duration required. Please try again with a longer audio sample. |
| E0808 | The audio sample provided for voice cloning is too long. The error message will specify the maximum duration allowed. Please try again with a shorter audio sample. |
| E0809 | The request was flagged as attempting to generate a child voice, which violates our Acceptable Use Policy. Please modify your description to use an adult voice. |
| E0810 | Unable to retrieve the cloned voice. Please upgrade to Creator plan or higher to access cloned voices. |
| E0811 | The service is currently experiencing high traffic and your request was rate limited. Please try again later. |
| E0812 | A voice with the specified name already exists. Please choose a different name for your cloned voice. |
| E0813 | A voice created with Octave 2 cannot be used with Octave 1. Please use Octave 2 with this voice. |
| E0814 | Instant voice cloning is not available for Octave 1. Please use Octave 2 for instant voice cloning. |
| E0815 | A voice must be specified when using Octave 2. Please include a voice in all utterances when using Octave 2. |
| E0816 | The supplied media file exceeds the maximum file size. Please try again with a smaller file. |
WebSocket status codes
| Code | Description |
|---|---|
| 1000 | close_normal indicates an expected, intentional disconnect initiated by the server, such as when the built-in hang-up tool closes the connection. This code is also used for inactivity timeout and max duration timeout, indicating that the WebSocket connection was closed due to remaining inactive for too long or exceeding the maximum allowed duration. |
| 1008 | policy_violation occurs when the WebSocket connection encounters an issue that cannot be recovered due to user error. Please review your request and ensure it adheres to the APIs guidelines and policies. |
| 1011 | server_error indicates that the WebSocket connection encountered an issue that cannot be recovered due to an internal Hume server error. Please try again later or contact support if the issue persists. |
Service errors
If you encounter an error code starting with I (for example, error code I0100), it indicates an outage or a bug in a Hume service. Our team will already have been alerted of the internal error, but if you need immediate assistance please reach out to our support team.
Warnings
Warnings indicate that the payload was configured correctly, but no results could be returned.
| Code | Description |
|---|---|
| W0101 | No vocal bursts could be detected in the media. |
| W0102 | No face meshes could be detected in the media. |
| W0103 | No faces could be detected in the media. |
| W0104 | No emotional language could be detected in the media. |
| W0105 | No speech could be detected in the media. |
| W0106 | No dynamic variable(s) found matching the one(s) specified. |
| W0107 | A long user input message was detected. Long user messages without associated audio input can cause voice hallucinations, especially at the start of a chat. For better results, use the system prompt to set context at the start of the chat. |
| W0108 | A long assistant input message was detected. Long assistant messages without associated audio input can cause voice hallucinations, especially at the start of a chat. For better results, use the system prompt to set context at the start of the chat. |
| W0109 | The user input message exceeds the maximum allowed length and was ignored. Please reduce the message length. |
| W0110 | The assistant input message exceeds the maximum allowed length and was ignored. Please reduce the message length. |
| W0111 | Using both an external language model and context injection simultaneously is not supported. Context injection has been automatically disabled. |
| W0112 | The system prompt sent through session settings was blocked by our content filter. The system prompt was not updated. Please review the content of your system prompt. |
| W0113 | Some variable attributes have not been provided values. This may result in incomplete text formatting. Please ensure all variable attributes are assigned values. |
