Eleven Turbo v2 is ElevenLabs’ English-only text-to-speech model for applications that need responsive spoken replies. It receives the prepared text of an utterance and returns audio in a selected voice. The manufacturer identifies Turbo v2 separately from multilingual Turbo v2.5 and from the Flash line. Its useful role is an English voice response, such as a confirmation, a short explanation or the next instruction in a conversational interface.
English is the defining language boundary of this edition. Supplying another language does not give Turbo v2 the multilingual profile of v2.5. Choose a voice with the accent and delivery needed for the English script. A warm conversational voice, a restrained narrator and an energetic character can make the same sentence sound different, so the selected voice is part of the brief rather than a fixed default determined by the model name.
Prepare a clean spoken script. The model synthesises the words supplied to it; it does not decide whether an action succeeded or generate the application’s reasoning. For an assistant reply, include one clear result and a natural next step. An illustrative line might confirm that a document was received and ask for its missing reference number. Keep internal instructions and metadata outside the words meant to be heard, because ordinary descriptive text can itself be spoken.
Names, abbreviations and numbers need deliberate preparation. Write an identifier as separate digits when it must be repeated that way, and expand an abbreviation when the listener should hear its full meaning. For a date, use an unambiguous spoken form. Pronunciation aliases or alternative spellings can supply a preferred way to say a difficult name. Retain the original display spelling separately from the spoken form if the application also shows the message as text.
The producer’s voice settings influence consistency, resemblance and pace. In its shared TTS product guide, the speed setting uses 1.0 for unchanged speed and a range from 0.7 to 1.2; extreme adjustments may affect the result. Stability changes the variability and emotional range, while similarity controls resemblance to the selected voice. These controls do not make synthesis deterministic or establish an exact duration for a line. Punctuation and complete sentence structure remain important to how the words are delivered.
The producer’s exact Turbo v2 API limit is 30,000 characters per request. This is an input ceiling rather than a fixed audio duration; use complete sentences or sections when preparing longer text. ElevenLabs’ TTS format family includes MP3 for general listening, uncompressed 16-bit PCM, telephony encodings such as μ-law and A-law, and Opus. A streaming workflow can return audio progressively, while a complete text request can be collected as a recording. Choose the output for the playback destination and keep the actual script with the selected audio. For a longer explanation, divide the text at meaningful boundaries instead of asking a listener to follow a single extended list.
For a practical English support response, prepare the exact result, a clearly spoken name or identifier and the next action. Review the relevant part of the recording for intelligibility, accent and natural rhythm. The producer documents nondeterministic output, so the same settings can still produce a slightly different performance. The reusable artifact is the selected speech recording together with its prepared wording and voice settings, for an assistant, notification, tutorial cue or short recorded explanation.
", "aboutText": "Eleven Turbo v2 is ElevenLabs’ English-only text-to-speech model for applications that need responsive spoken replies. It receives the prepared text of an utterance and returns audio in a selected voice. The manufacturer identifies Turbo v2 separately from multilingual Turbo v2.5 and from the Flash line. Its useful role is an English voice response, such as a confirmation, a short explanation or the next instruction in a conversational interface.\n\nEnglish is the defining language boundary of this edition. Supplying another language does not give Turbo v2 the multilingual profile of v2.5. Choose a voice with the accent and delivery needed for the English script. A warm conversational voice, a restrained narrator and an energetic character can make the same sentence sound different, so the selected voice is part of the brief rather than a fixed default determined by the model name.\n\nPrepare a clean spoken script. The model synthesises the words supplied to it; it does not decide whether an action succeeded or generate the application’s reasoning. For an assistant reply, include one clear result and a natural next step. An illustrative line might confirm that a document was received and ask for its missing reference number. Keep internal instructions and metadata outside the words meant to be heard, because ordinary descriptive text can itself be spoken.\n\nNames, abbreviations and numbers need deliberate preparation. Write an identifier as separate digits when it must be repeated that way, and expand an abbreviation when the listener should hear its full meaning. For a date, use an unambiguous spoken form. Pronunciation aliases or alternative spellings can supply a preferred way to say a difficult name. Retain the original display spelling separately from the spoken form if the application also shows the message as text.\n\nThe producer’s voice settings influence consistency, resemblance and pace. In its shared TTS product guide, the speed setting uses 1.0 for unchanged speed and a range from 0.7 to 1.2; extreme adjustments may affect the result. Stability changes the variability and emotional range, while similarity controls resemblance to the selected voice. These controls do not make synthesis deterministic or establish an exact duration for a line. Punctuation and complete sentence structure remain important to how the words are delivered.\n\nThe producer’s exact Turbo v2 API limit is 30,000 characters per request. This is an input ceiling rather than a fixed audio duration; use complete sentences or sections when preparing longer text. ElevenLabs’ TTS format family includes MP3 for general listening, uncompressed 16-bit PCM, telephony encodings such as μ-law and A-law, and Opus. A streaming workflow can return audio progressively, while a complete text request can be collected as a recording. Choose the output for the playback destination and keep the actual script with the selected audio. For a longer explanation, divide the text at meaningful boundaries instead of asking a listener to follow a single extended list.\n\nFor a practical English support response, prepare the exact result, a clearly spoken name or identifier and the next action. Review the relevant part of the recording for intelligibility, accent and natural rhythm. The producer documents nondeterministic output, so the same settings can still produce a slightly different performance. The reusable artifact is the selected speech recording together with its prepared wording and voice settings, for an assistant, notification, tutorial cue or short recorded explanation.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "1374677d489ac962746fd9ed2f59c07e36283d0847c5d22ab4ce9ef29c1c7933", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "elevenlabs/eleven-turbo-v2Eleven Turbo v2 is ElevenLabs’ English-only text-to-speech edition for responsive voice applications. It speaks the supplied text in a selected voice, suiting assistant replies, notifications and short explanations prepared for listening.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Eleven Turbo v2 is ElevenLabs’ English-only text-to-speech model for applications that need responsive spoken replies. It receives the prepared text of an utterance and returns audio in a selected voice. The manufacturer identifies Turbo v2 separately from multilingual Turbo v2.5 and from the Flash line. Its useful role is an English voice response, such as a confirmation, a short explanation or the next instruction in a conversational interface.
English is the defining language boundary of this edition. Supplying another language does not give Turbo v2 the multilingual profile of v2.5. Choose a voice with the accent and delivery needed for the English script. A warm conversational voice, a restrained narrator and an energetic character can make the same sentence sound different, so the selected voice is part of the brief rather than a fixed default determined by the model name.
Prepare a clean spoken script. The model synthesises the words supplied to it; it does not decide whether an action succeeded or generate the application’s reasoning. For an assistant reply, include one clear result and a natural next step. An illustrative line might confirm that a document was received and ask for its missing reference number. Keep internal instructions and metadata outside the words meant to be heard, because ordinary descriptive text can itself be spoken.
Names, abbreviations and numbers need deliberate preparation. Write an identifier as separate digits when it must be repeated that way, and expand an abbreviation when the listener should hear its full meaning. For a date, use an unambiguous spoken form. Pronunciation aliases or alternative spellings can supply a preferred way to say a difficult name. Retain the original display spelling separately from the spoken form if the application also shows the message as text.
The producer’s voice settings influence consistency, resemblance and pace. In its shared TTS product guide, the speed setting uses 1.0 for unchanged speed and a range from 0.7 to 1.2; extreme adjustments may affect the result. Stability changes the variability and emotional range, while similarity controls resemblance to the selected voice. These controls do not make synthesis deterministic or establish an exact duration for a line. Punctuation and complete sentence structure remain important to how the words are delivered.
The producer’s exact Turbo v2 API limit is 30,000 characters per request. This is an input ceiling rather than a fixed audio duration; use complete sentences or sections when preparing longer text. ElevenLabs’ TTS format family includes MP3 for general listening, uncompressed 16-bit PCM, telephony encodings such as μ-law and A-law, and Opus. A streaming workflow can return audio progressively, while a complete text request can be collected as a recording. Choose the output for the playback destination and keep the actual script with the selected audio. For a longer explanation, divide the text at meaningful boundaries instead of asking a listener to follow a single extended list.
For a practical English support response, prepare the exact result, a clearly spoken name or identifier and the next action. Review the relevant part of the recording for intelligibility, accent and natural rhythm. The producer documents nondeterministic output, so the same settings can still produce a slightly different performance. The reusable artifact is the selected speech recording together with its prepared wording and voice settings, for an assistant, notification, tutorial cue or short recorded explanation.
POST /v1/audio/speechtextaudio| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits elevenlabs/eleven-turbo-v2 | Default— |
Fieldinput | Typestring | RequirementRequired | Values & limits Minimum length: 1 Maximum length: 30,000 Unit: Unicode characters | Default— |
Fieldvoice | Typestring | RequirementRequired | Values & limits george, sarah, adam, alice, bella, bill, brian, callum, charlie, chris, daniel, eric, harry, jessica, laura, liam, lily, matilda, river, roger, will | Default— |
Fieldresponse_format | Typestring | RequirementRequired | Values & limits mp3 | Default— |
text_to_speech · Required: input
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, input, voice, response_format |
Parametervoice_ids | Contractgeorge, sarah, adam, alice, bella, bill, brian, callum, charlie, chris, daniel, eric, harry, jessica, laura, liam, lily, matilda, river, roger, will |
Parameterresponse_format | Contractmp3 |
Parametermax_input_characters | Contract30000 |
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 | Billing unit | Charge |
|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | 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 |
| Configurationinput character | Rate schedule— | Billing unitper input character | Charge Input · input character $0.00008 per input character |
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
| Configuration | Billing conditions | Charge |
|---|---|---|
| ConfigurationElevenLabs: Eleven Turbo v2 · Default configuration | Billing conditionsDefault configuration | Charge Input · Input characters $0.00004 per input character |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_VOICE_ID:?Choose an accepted voice ID from this exact model profile}"\nexport AILOOT_VOICE_ID\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "elevenlabs/eleven-turbo-v2", "input": "Good afternoon! This is a short voice take."}')\nvoice=os.environ["AILOOT_VOICE_ID"]\nallowed=json.loads('["george", "sarah", "adam", "alice", "bella", "bill", "brian", "callum", "charlie", "chris", "daniel", "eric", "harry", "jessica", "laura", "liam", "lily", "matilda", "river", "roger", "will"]')\nif voice not in allowed: raise SystemExit("Choose an accepted voice ID from this exact model profile")\np["voice"]=voice\np["response_format"]="mp3"\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 elevenlabs/eleven-turbo-v2
Use the method paths shown above.