Speech to English API¶

Translate audio from any language to English text with Amazon Transcribe + Translate or Amazon Bedrock audio-capable models through an OpenAI-compatible interface.

At a glance¶

• No source language to declare — Amazon Transcribe identifies the language spoken and Amazon Translate renders it in English, see Working with Amazon Transcribe and Amazon Translate.
• Two ways to English — amazon.transcribe runs the transcribe-then-translate pipeline; a Bedrock model that accepts the SPEECH modality, such as Amazon Nova Sonic, answers in English in a single request, see Models.
• Five output formats — text, json, verbose_json, srt and vtt, the last three on Amazon Transcribe, see Feature compatibility.
• Subtitle cues keep their original timing — SRT and VTT carry the timings Amazon Transcribe produced, with English text in them, see Working with Amazon Transcribe and Amazon Translate.
• Amazon Translate glossaries and formality per request — TerminologyNames and Settings travel in the JSON body beside the OpenAI fields, see Provider-Specific Parameters.
• amazon.transcribe rejects prompt and temperature, and a source language Amazon Translate does not cover is refused — see Limits and behaviour to know.

curl -X POST "$BASE/v1/audio/translations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F file=@spanish-interview.mp3 \
  -F model=amazon.transcribe

Endpoints¶

Feature compatibility¶

Models¶

Amazon Models¶

Mistral Models¶

Amazon Nova Sonic¶

Name this model to translate through Amazon Nova Sonic instead of Amazon Transcribe and Amazon Translate. The model listens to the audio and answers with the English text directly, in a single request.

Other Amazon Bedrock Models¶

Any Amazon Bedrock model that accepts the SPEECH input modality through the Converse API can also translate audio out of the box: the gateway sends the audio together with a translation prompt and returns the model's English text output.

Working with Amazon Transcribe and Amazon Translate¶

Amazon Transcribe Features¶

Model & Features:

• Use amazon.transcribe with the same interface as OpenAI's Whisper API
• Or use OpenAI model names directly: whisper-1, gpt-transcribe, gpt-live-transcribe, gpt-4o-transcribe, and gpt-4o-mini-transcribe work out of the box (they map to amazon.transcribe)
• Automatic transcription + translation pipeline in one request
• Multiple output formats: text, json, verbose_json, srt, vtt
• Automatic source language detection — no parameter to set
• Smart Subtitle Translation : Subtitle timing is preserved during translation

Provider-Specific Parameters¶

amazon.transcribe first transcribes the audio, then translates it, and each step has its own provider-specific parameters — both reachable via the same application/json request body.

Transcription step (Amazon Transcribe): the same extra parameters documented for /v1/audio/transcriptions (ContentRedaction, VocabularyName, VocabularyFilterName/VocabularyFilterMethod, ShowAlternatives/MaxAlternatives, ChannelIdentification, ToxicityDetection, IdentifyMultipleLanguages/LanguageOptions, LanguageIdSettings, ModelSettings) apply here too.

Translation step (Amazon Translate): Settings and TerminologyNames control the English output register and glossary:

{
  "model": "amazon.transcribe",
  "file": "data:audio/mp3;base64,<base64-encoded-audio>",
  "Settings": {
    "Formality": "FORMAL",
    "Profanity": "MASK"
  },
  "TerminologyNames": ["MyProductGlossary"]
}

• Settings.Formality (FORMAL or INFORMAL): Register of the translated text, for languages that support formality
• Settings.Profanity (MASK): Mask profane words and phrases in the translation
• Settings.Brevity (ON): Per AWS Translate, reduces the length of the translation output for most translations; unsupported language pairs silently ignore it
• TerminologyNames (list): Apply one or more custom terminologies (domain-specific glossaries) to the translation

Both settings apply consistently to the primary translated text and, for response_format=verbose_json, to every per-segment translation.

Invalid Settings values (e.g. an unsupported Formality) are rejected with HTTP 400 before any partial translation occurs.

Limits and behaviour to know¶

• With amazon.transcribe, the prompt and temperature parameters are rejected with an error to ensure consistent translation accuracy. Bedrock audio models accept both.
• verbose_json translates the transcript twice, once whole and once per segment, so it costs roughly double the Amazon Translate characters of text or json for the same audio — see Provider-Specific Parameters.
• verbose_json segments carry the translated text on the source cue's start and end; their seek, temperature, tokens, avg_logprob and no_speech_prob fields are the same placeholders as on /v1/audio/transcriptions.

Request headers¶

This endpoint supports standard Bedrock headers for enhanced control over your requests. All headers are optional and can be combined as needed.

Content Safety (Guardrails)¶

The guardrail evaluates the English translation the model produced, not the audio sent. X-Amzn-Bedrock-Trace is accepted but has no effect on this route — no guardrail trace is returned.

Performance Optimization¶

Both apply only to models translated through the Amazon Bedrock runtime. They have no effect on amazon.transcribe, which is served by Amazon Transcribe and AWS Translate, nor on Amazon Nova Sonic, which is served over its own bidirectional stream.

Example with headers:

curl -X POST "$BASE/v1/audio/translations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "X-Amzn-Bedrock-GuardrailIdentifier: your-guardrail-id" \
  -H "X-Amzn-Bedrock-GuardrailVersion: 1" \
  -F file=@spanish-interview.mp3 \
  -F model=amazon.transcribe \
  -F response_format=json

Try it¶

Translate foreign audio to English text:

curl -X POST "$BASE/v1/audio/translations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F file=@spanish-interview.mp3 \
  -F model=amazon.transcribe \
  -F response_format=json

Translate via JSON body (MCP and AI agents):

When using MCP tools or HTTP clients that cannot construct multipart requests, pass the audio as a data URI or URL:

# Data URI (inline base64)
curl -X POST "$BASE/v1/audio/translations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "file": "data:audio/mp3;base64,<base64-encoded-audio>",
    "model": "amazon.transcribe"
  }'

# HTTPS URL (server fetches the audio)
curl -X POST "$BASE/v1/audio/translations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "file": "https://example.com/audio.mp3",
    "model": "amazon.transcribe"
  }'

# Files API reference (file-id: URI scheme)
curl -X POST "$BASE/v1/audio/translations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "file": "file-id:file-0190c51c7de7455d9b8c2efe27dfbf67",
    "model": "amazon.transcribe"
  }'

See Files API → Referencing Uploaded Files for the full description of the file-id: URI scheme.

Translate foreign audio to English subtitles:

curl -OJ -X POST "$BASE/v1/audio/translations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F file=@spanish-interview.mp3 \
  -F model=amazon.transcribe \
  -F response_format=srt

Next steps¶

Next: Models API · Speech to Text API · AWS_TRANSCRIBE_S3_BUCKET, where jobs are staged · Speech-to-text IAM permissions · Text-translation IAM permissions