TTS-1 HD is OpenAI's text-to-speech model optimized for audio quality. A prepared script is its input and spoken audio is its output. The HD choice is distinct from TTS-1's speed-oriented profile: OpenAI describes TTS-1 as lower latency but lower quality. HD is therefore a useful narration choice when the finished voice track matters more than beginning playback as quickly as possible. A written article, a lesson passage or a polished explanation can become a spoken asset.
The core inputs are the selected model, the exact text and a voice. The manufacturer's speech reference limits the script to 4096 characters per request. That describes written input length, not an audio duration guarantee. Prepare a script that can be understood when heard: expand ambiguous abbreviations, decide how quantities are spoken and keep each passage coherent. For a longer lesson or article, divide the text at meaningful boundaries and retain the order in which the resulting passages will be used.
The current OpenAI guide lists nine built-in choices for TTS-1 HD: alloy, ash, coral, echo, fable, onyx, nova, sage and shimmer. The voices are optimized for English, while the text-to-speech guide supports generating speech in several languages by supplying text in the required language. A voice comparison is most useful with the same representative script, including the names and specialist vocabulary that will appear in the final material. Keep voice and speed consistent when multiple clips form one narration.
MP3 is the default output. Opus and AAC provide alternative compressed audio formats; FLAC provides lossless compression; WAV provides uncompressed audio. PCM supplies raw 24 kHz, 16-bit signed little-endian samples without a file header. These choices serve different uses: a compact distributable file, a streaming asset or audio to pass into an editing workflow. OpenAI recommends WAV or PCM for quicker response times where decoding overhead matters. Choosing a file format does not change the script or add a separate voice-control model.
Speech can be delivered in chunks, allowing a player to begin before the complete audio file is ready. This is text-to-audio streaming; it does not establish a bidirectional voice conversation. The reference supports a speed value from 0.25 to 4.0, with 1.0 as the default. The separate natural-language instructions field does not work with TTS-1 HD, and SSE event output is not supported for this model. Script, preset voice, speed and output format are the documented controls, rather than the newer speech models' prompted accent or emotional-direction interface.
The language guide includes Russian, Ukrainian, English, French, German, Spanish, Portuguese, Italian, Chinese, Japanese, Korean, Arabic, Hindi and Kazakh among its supported languages. Prepare the script in the target language; synthesis renders that text rather than translating it. For learning content, make definitions and section transitions clear. For an explanatory audio passage, prepare the exact message and any names that must be heard. The voice's English optimization remains relevant when evaluating how a particular language and vocabulary sound.
A practical HD workflow produces an audio passage to listen to, review and then include in the finished material. Check that every sentence was rendered, that names and quantities were pronounced acceptably and that the chosen pacing supports comprehension. Preserve the written script beside the audio so a correction can be traced to the relevant passage. OpenAI requires a clear disclosure that the generated voice is artificial. HD describes the quality-oriented TTS family; it does not by itself promise exact timing, a custom speaker identity or the expressive controls of a different model.
", "aboutText": "TTS-1 HD is OpenAI's text-to-speech model optimized for audio quality. A prepared script is its input and spoken audio is its output. The HD choice is distinct from TTS-1's speed-oriented profile: OpenAI describes TTS-1 as lower latency but lower quality. HD is therefore a useful narration choice when the finished voice track matters more than beginning playback as quickly as possible. A written article, a lesson passage or a polished explanation can become a spoken asset.\n\nThe core inputs are the selected model, the exact text and a voice. The manufacturer's speech reference limits the script to 4096 characters per request. That describes written input length, not an audio duration guarantee. Prepare a script that can be understood when heard: expand ambiguous abbreviations, decide how quantities are spoken and keep each passage coherent. For a longer lesson or article, divide the text at meaningful boundaries and retain the order in which the resulting passages will be used.\n\nThe current OpenAI guide lists nine built-in choices for TTS-1 HD: alloy, ash, coral, echo, fable, onyx, nova, sage and shimmer. The voices are optimized for English, while the text-to-speech guide supports generating speech in several languages by supplying text in the required language. A voice comparison is most useful with the same representative script, including the names and specialist vocabulary that will appear in the final material. Keep voice and speed consistent when multiple clips form one narration.\n\nMP3 is the default output. Opus and AAC provide alternative compressed audio formats; FLAC provides lossless compression; WAV provides uncompressed audio. PCM supplies raw 24 kHz, 16-bit signed little-endian samples without a file header. These choices serve different uses: a compact distributable file, a streaming asset or audio to pass into an editing workflow. OpenAI recommends WAV or PCM for quicker response times where decoding overhead matters. Choosing a file format does not change the script or add a separate voice-control model.\n\nSpeech can be delivered in chunks, allowing a player to begin before the complete audio file is ready. This is text-to-audio streaming; it does not establish a bidirectional voice conversation. The reference supports a speed value from 0.25 to 4.0, with 1.0 as the default. The separate natural-language instructions field does not work with TTS-1 HD, and SSE event output is not supported for this model. Script, preset voice, speed and output format are the documented controls, rather than the newer speech models' prompted accent or emotional-direction interface.\n\nThe language guide includes Russian, Ukrainian, English, French, German, Spanish, Portuguese, Italian, Chinese, Japanese, Korean, Arabic, Hindi and Kazakh among its supported languages. Prepare the script in the target language; synthesis renders that text rather than translating it. For learning content, make definitions and section transitions clear. For an explanatory audio passage, prepare the exact message and any names that must be heard. The voice's English optimization remains relevant when evaluating how a particular language and vocabulary sound.\n\nA practical HD workflow produces an audio passage to listen to, review and then include in the finished material. Check that every sentence was rendered, that names and quantities were pronounced acceptably and that the chosen pacing supports comprehension. Preserve the written script beside the audio so a correction can be traced to the relevant passage. OpenAI requires a clear disclosure that the generated voice is artificial. HD describes the quality-oriented TTS family; it does not by itself promise exact timing, a custom speaker identity or the expressive controls of a different model.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "61b3faf5bb2c51b34af001509f53e37ab075aff9a8f0c05b318eb6f140eff9a6", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "openai/tts-1-hdTTS-1 HD converts written text into higher-quality spoken audio with selectable preset voices, speed and six output formats. OpenAI positions HD for narration quality rather than the lower-latency profile of TTS-1, making it useful for finished readouts, learning material and edited audio passages.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
TTS-1 HD is OpenAI's text-to-speech model optimized for audio quality. A prepared script is its input and spoken audio is its output. The HD choice is distinct from TTS-1's speed-oriented profile: OpenAI describes TTS-1 as lower latency but lower quality. HD is therefore a useful narration choice when the finished voice track matters more than beginning playback as quickly as possible. A written article, a lesson passage or a polished explanation can become a spoken asset.
The core inputs are the selected model, the exact text and a voice. The manufacturer's speech reference limits the script to 4096 characters per request. That describes written input length, not an audio duration guarantee. Prepare a script that can be understood when heard: expand ambiguous abbreviations, decide how quantities are spoken and keep each passage coherent. For a longer lesson or article, divide the text at meaningful boundaries and retain the order in which the resulting passages will be used.
The current OpenAI guide lists nine built-in choices for TTS-1 HD: alloy, ash, coral, echo, fable, onyx, nova, sage and shimmer. The voices are optimized for English, while the text-to-speech guide supports generating speech in several languages by supplying text in the required language. A voice comparison is most useful with the same representative script, including the names and specialist vocabulary that will appear in the final material. Keep voice and speed consistent when multiple clips form one narration.
MP3 is the default output. Opus and AAC provide alternative compressed audio formats; FLAC provides lossless compression; WAV provides uncompressed audio. PCM supplies raw 24 kHz, 16-bit signed little-endian samples without a file header. These choices serve different uses: a compact distributable file, a streaming asset or audio to pass into an editing workflow. OpenAI recommends WAV or PCM for quicker response times where decoding overhead matters. Choosing a file format does not change the script or add a separate voice-control model.
Speech can be delivered in chunks, allowing a player to begin before the complete audio file is ready. This is text-to-audio streaming; it does not establish a bidirectional voice conversation. The reference supports a speed value from 0.25 to 4.0, with 1.0 as the default. The separate natural-language instructions field does not work with TTS-1 HD, and SSE event output is not supported for this model. Script, preset voice, speed and output format are the documented controls, rather than the newer speech models' prompted accent or emotional-direction interface.
The language guide includes Russian, Ukrainian, English, French, German, Spanish, Portuguese, Italian, Chinese, Japanese, Korean, Arabic, Hindi and Kazakh among its supported languages. Prepare the script in the target language; synthesis renders that text rather than translating it. For learning content, make definitions and section transitions clear. For an explanatory audio passage, prepare the exact message and any names that must be heard. The voice's English optimization remains relevant when evaluating how a particular language and vocabulary sound.
A practical HD workflow produces an audio passage to listen to, review and then include in the finished material. Check that every sentence was rendered, that names and quantities were pronounced acceptably and that the chosen pacing supports comprehension. Preserve the written script beside the audio so a correction can be traced to the relevant passage. OpenAI requires a clear disclosure that the generated voice is artificial. HD describes the quality-oriented TTS family; it does not by itself promise exact timing, a custom speaker identity or the expressive controls of a different model.
POST /v1/audio/speechtextaudio| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/tts-1-hd | Default— |
Fieldinput | Typestring | RequirementRequired | Values & limits Minimum length: 1 Maximum length: 4,096 Unit: Unicode characters | Default— |
Fieldvoice | Typestring | RequirementRequired | Values & limits alloy | Default— |
text_to_speech · Required: input
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, input, voice |
Parametervoice_ids | Contractalloy |
Parametermax_input_characters | Contract4096 |
Parameterother_options | Contractfalse |
Parameterinput | Contractexact UTF-8 text; Unicode character count without normalization |
Parametermaterial_types | Contracttext |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Select exact voice from this model profile.
Input characters and audio seconds are different meters.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Billable quantity | Billing quantity | Billing unit | Charge |
|---|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Billable quantity— | Billing quantity— | Billing unit— | Charge Input · Input tokens — / 1K tokens Output · Output tokens — / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationUltra | Rate schedule— | Billable quantityEach Unicode code point counts as one character, including Han characters. | Billing quantity— | Billing unitper 1000 input character | Charge Input · input character $0.06 per 1000 input character |
| ConfigurationPer request | Rate schedule— | Billable quantity— | Billing quantityone request | Billing unit— | Charge Input $0 per request |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "openai/tts-1-hd", "input": "Good afternoon! This is a short voice take.", "voice": "alloy"}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/speech \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o speech.mp3\nmp3
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o media-assets.json\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_MEDIA_TASK_ID:?Set the actual ID returned by the response or media-library metadata}"\nexport AILOOT_MEDIA_TASK_ID\nresource_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ["AILOOT_MEDIA_TASK_ID"],safe=""))')\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/media/tasks/$resource_id" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o media-task.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("media-task.json").read_text())))\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_ASSET_ID:?Set the actual ID returned by the response or media-library metadata}"\nexport AILOOT_ASSET_ID\nresource_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ["AILOOT_ASSET_ID"],safe=""))')\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/media/assets/$resource_id" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o media-asset.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("media-asset.json").read_text())))\nPY_RESULT\nKeep every complete returned response, file and content part.
Keep the complete binary result and headers. If JSON/multiple outputs are returned, retain every data item and fetch each actual signed asset URL.
Retain original operation_id/X-Client-Request-ID for reconciliation without resubmission; no dedicated audio poll route.
| Field | Type |
|---|---|
Fieldbinary audio | Typebytes |
Fieldresponse headers | Typeheaders |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Ailoot Ultra openai/tts-1-hd
Use the method paths shown above.