> ## Documentation Index > Fetch the complete documentation index at: https://docs.modulate.ai/llms.txt > Use this file to discover all available pages before exploring further. # Speech-to-Text Transcription Batch Multilingual > Multilingual batch transcription with automatic language detection, speaker diarization, emotion and accent detection, and PII/PHI tagging. ## OpenAPI ````yaml api/velma_2_stt_batch.yaml POST /api/velma-2-stt-batch openapi: 3.1.0 info: title: Velma 2 STT Batch API version: 0.0.0 description: | Batch transcription of audio files via HTTP POST. Supports multilingual transcription with automatic per-utterance language detection, returning the full transcript plus per-utterance metadata (timing and speaker). Optional per-request capabilities - speaker diarization, emotion detection, accent detection, synthetic voice (deepfake) detection, and PII/PHI tagging - add the corresponding signals to each utterance. servers: - url: https://platform.modulate.ai description: Modulate STT Batch Server security: - ApiKeyAuth: [] paths: /api/velma-2-stt-batch: post: summary: Transcribe audio file with automatic language detection description: > Transcribe an audio file and return the full transcript with per-utterance metadata. Language is detected automatically for each utterance, so different utterances in the same file may be identified as different languages when code-switching occurs. operationId: transcribeMultilingualBatch requestBody: required: true content: multipart/form-data: schema: type: object required: - upload_file properties: upload_file: type: string format: binary description: > Audio file to transcribe. Supported formats: AAC, AIFF, FLAC, MP3, MP4, MOV, OGG, Opus, WAV, WebM. Maximum file size: 100MB. Empty files are rejected. speaker_diarization: type: boolean default: true description: > Speaker diarization identifies different speakers in the audio. When enabled, each utterance includes a speaker identifier (e.g., 1, 2). emotion_signal: type: boolean default: false description: > Emotion detection for each utterance. When enabled, each utterance includes an emotion signal detected from the speaker's voice. accent_signal: type: boolean default: false description: > Accent detection for each utterance. When enabled, each utterance includes an accent signal detected from the speaker's voice. deepfake_signal: type: boolean default: false description: > Synthetic voice (deepfake) detection for each utterance. When enabled, each utterance includes a deepfake_score indicating the likelihood that the speech is AI-generated. The score ranges from 0.0 (likely natural) to 1.0 (likely synthetic). pii_phi_tagging: type: boolean default: false description: > PII/PHI tagging in utterance text. When enabled, personally identifiable information and personal health information are wrapped with appropriate tags in the transcription text. language: type: string pattern: ^[A-Za-z]{2,3}([-_][A-Za-z0-9]+)*$ description: > Optional language hint as a case-insensitive ISO 639-1 code (e.g. "en", "fr"). BCP 47 region/script subtags (e.g. "en-US") are accepted; only the primary language subtag is used. When omitted, the language is detected automatically for each utterance. config: type: string contentMediaType: application/json contentSchema: $ref: '#/components/schemas/STTConfig' description: > Optional JSON-encoded STT configuration. A field that has a matching top-level form parameter overrides it; an omitted field falls back to the form parameter. Supply custom_terms here, e.g. `config={"custom_terms":["Modulate",{"term":"Velma","pronunciations":["VEL-muh"]}]}`. encoding: config: contentType: application/json responses: '200': description: Transcription completed successfully content: application/json: schema: $ref: '#/components/schemas/TranscriptionResponse' examples: multilingual: summary: Transcription with multiple languages value: text: Hello, how are you? Bonjour, ça va? duration_ms: 5000 utterances: - utterance_uuid: e5f6a7b8-c9d0-1234-efab-345678901234 text: Hello, how are you? start_ms: 0 duration_ms: 2000 speaker: 1 language: en emotion: Neutral accent: American deepfake_score: null - utterance_uuid: f6a7b8c9-d0e1-2345-fabc-456789012345 text: Bonjour, ça va? start_ms: 2500 duration_ms: 2500 speaker: 2 language: fr emotion: Happy accent: British deepfake_score: null '400': description: | Bad request - The submitted audio was rejected: an unsupported file extension, an empty file, or audio that could not be processed (for example, corrupted data or content that does not match a supported format); or a request parameter value was invalid (for example, `language`). content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: invalid_format: summary: Invalid file format value: detail: >- Unsupported file format. Supported formats: .aac, .aiff, .flac, .mov, .mp3, .mp4, .ogg, .opus, .wav, .webm. empty_file: summary: Empty file value: detail: The uploaded file is empty. unprocessable_audio: summary: Audio could not be processed value: detail: >- The audio could not be processed. It may be corrupted or in an unsupported format. invalid_language: summary: Invalid language code value: detail: >- Invalid language='english'. Expected an ISO 639-1 language code (e.g. 'en', 'fr'). invalid_config: summary: Invalid config value value: detail: Invalid configuration. invalid_config_fields: summary: >- Invalid config fields - the field list names the offending config fields value: detail: >- Invalid configuration. Invalid or malformed field(s): deepfake_signal. bad_value: summary: Invalid request value value: detail: Invalid request. '401': description: Unauthorized - the API key is missing or invalid content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: missing_api_key: summary: API key header absent value: detail: Missing API key. invalid_api_key: summary: API key not recognized value: detail: Invalid API key. '403': description: Forbidden - the request is not permitted content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: not_permitted: summary: Request not permitted value: detail: This request is not permitted. model_access_denied: summary: API key lacks access to this model value: detail: This API key does not have access to this model. '413': description: >- Payload too large - the uploaded file exceeds the maximum allowed size content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: detail: The uploaded file is too large. '422': description: > Unprocessable Entity - a required request field is missing or malformed (for example, the `upload_file` part). content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '429': description: >- Too many requests - insufficient credits or a usage limit was reached content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: insufficient_credits: summary: Insufficient credits value: detail: Insufficient credits. concurrency_limit: summary: Concurrent request limit reached value: detail: >- Concurrent request limit reached. Please retry after your in-flight requests complete. monthly_limit: summary: Monthly usage limit reached value: detail: Monthly usage limit reached. '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: detail: Internal server error '502': description: Bad gateway - the request could not be completed content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: detail: Unable to complete the request. Please try again. components: schemas: TranscriptionResponse: type: object required: - text - duration_ms - utterances properties: text: type: string description: > The complete transcribed text from the audio file, containing all utterances concatenated together. This provides a full transcript of the audio content. Always present; may be an empty string when no speech was recognized. example: Hello everyone. Welcome to the meeting. duration_ms: type: integer minimum: 0 description: > The total duration of the processed audio in milliseconds. This value represents the actual audio duration and is used for usage tracking and billing purposes. example: 45000 utterances: type: array description: > Array of individual utterances detected in the audio, ordered by start time. Each utterance represents a continuous segment of speech, potentially from a specific speaker if diarization is enabled. Always present; may be an empty array when no speech was recognized. items: $ref: '#/components/schemas/Utterance' ErrorResponse: type: object required: - detail properties: detail: type: string description: Human-readable error message describing what went wrong example: >- Unsupported file format. Supported formats: .aac, .aiff, .flac, .mov, .mp3, .mp4, .ogg, .opus, .wav, .webm. HTTPValidationError: type: object properties: detail: type: array items: $ref: '#/components/schemas/ValidationError' Utterance: type: object required: - utterance_uuid - text - start_ms - duration_ms - speaker - language - emotion - accent - deepfake_score properties: utterance_uuid: type: string format: uuid description: | Unique identifier for this utterance. example: a1b2c3d4-e5f6-7890-abcd-ef1234567890 text: type: string description: > The transcribed text for this utterance. Represents a single continuous segment of speech. example: Hello everyone. start_ms: type: integer minimum: 0 description: > The start time of this utterance in milliseconds, relative to the beginning of the audio file. Allows precise synchronization with the original audio. example: 0 duration_ms: type: integer minimum: 0 description: | The duration of this utterance in milliseconds. example: 2500 speaker: type: integer description: > Speaker number for this utterance (1-indexed). When speaker diarization is enabled, this identifies which speaker produced this utterance. Speaker numbers are consistent within a single audio file but may vary between different files. example: 1 language: type: string description: > The automatically detected language code for this utterance (e.g., "en" for English, "fr" for French). example: en emotion: oneOf: - type: string - type: 'null' description: > Detected emotion signal for this utterance. Null if emotion detection is disabled. Possible values are: Angry, Disgusted, Afraid, Happy, Neutral, Other, Sad, Surprised, and Unknown. example: Neutral accent: oneOf: - type: string - type: 'null' description: > Detected accent signal for this utterance. Null if accent detection is disabled. Possible values include: American, British, Australian, Southern, Indian, Irish, Scottish, Eastern_European, African, Asian, Latin_American, Middle_Eastern, Unknown. example: American deepfake_score: oneOf: - type: number format: double minimum: 0 maximum: 1 - type: 'null' description: > Synthetic voice (deepfake) detection score for this utterance. Null if deepfake detection is disabled or if the utterance could not be analyzed. Values range from 0.0 (likely natural human speech) to 1.0 (likely AI-generated synthetic speech). example: 0.05 ValidationError: type: object required: - loc - msg - type properties: loc: type: array items: anyOf: - type: string - type: integer msg: type: string type: type: string securitySchemes: ApiKeyAuth: type: apiKey in: header name: X-API-Key description: API key used for authentication and usage tracking. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.