Eleven Flash v2 is ElevenLabs’ English-only speech-synthesis model for responsive voice applications. It takes a written utterance and produces spoken audio in the selected voice. The manufacturer positions Flash for real-time conversation and interactive experiences, such as assistant confirmations, spoken instructions and game responses. This named edition is separate from multilingual Flash v2.5 and the expressive v3 and v4 families.
English is the language profile of Flash v2. A voice can supply a regional accent and a particular tone, but it does not make this edition a multilingual model. Choose a voice that matches the intended listener and the purpose of the line. An assistant confirmation, an instructional narrator and an interactive character can require different cadence even when the factual content is the same. Prepare the actual English words that should be spoken before synthesis.
A request supports up to 30,000 characters. The producer’s approximate audio length beside this limit is not a fixed duration. For an interactive reply, keep one main thought and a clear ending; for a longer recording, divide related text at sentence or section boundaries. The shared TTS workflow documents neighbouring text or request context for preserving prosody across connected generations, so segmentation need not remove the relation between successive passages.
Flash v2’s pause workflow uses SSML break tags. The product guide gives <break time="1.5s" /> as a way to request a natural pause, with up to three seconds documented. The voice influences the delivery around the break, and excessive tags can cause speed changes, noise or artifacts. Use a break where the listener needs a transition, not between every word. Punctuation and ellipses can also influence timing but are less consistent and can add a hesitant tone.
Individual words can use SSML phoneme notation in IPA or CMU Arpabet. The manufacturer recommends CMU Arpabet for more predictable v2 pronunciation and says phoneme rules should be applied separately to each word of a multi-word name. Pronunciation dictionaries can retain the preferred phoneme or an alias for a recurring term; their matching is case-sensitive. This is different from v4’s native slash-wrapped IPA syntax and from the pronunciation profile of Flash v2.5.
Prepare reference codes, dates and abbreviations in the desired spoken form. The same digits can represent a quantity or an identifier, so specify whether the listener should hear a whole number or separate digits. Write the month and date unambiguously and expand abbreviations that should be spoken as words. Ordinary explanatory direction placed in the text may itself be read aloud; v3 and v4’s expressive audio tags are not the control profile described for this edition.
The producer’s format family includes MP3, uncompressed 16-bit PCM, μ-law and A-law for telephony, and Opus. The shared workflow can deliver a complete recording or return speech progressively. Voice settings influence stability, resemblance and pace, with a documented speed range of 0.7 to 1.2 and 1.0 unchanged. These settings guide a performance without guaranteeing an identical take or a precise final recording length.
For a practical English help message, give the result first, then one next step: confirm a saved selection, clearly pronounce the relevant field name and explain what the user can do next. For a tutorial, write a complete instruction and use a pause before the following action. Review the difficult names, numbers and transitions in the selected audio. Keep that take with its script and pronunciation preparation so it can become a reusable spoken cue, notification or assistant response.
", "aboutText": "Eleven Flash v2 is ElevenLabs’ English-only speech-synthesis model for responsive voice applications. It takes a written utterance and produces spoken audio in the selected voice. The manufacturer positions Flash for real-time conversation and interactive experiences, such as assistant confirmations, spoken instructions and game responses. This named edition is separate from multilingual Flash v2.5 and the expressive v3 and v4 families.\n\nEnglish is the language profile of Flash v2. A voice can supply a regional accent and a particular tone, but it does not make this edition a multilingual model. Choose a voice that matches the intended listener and the purpose of the line. An assistant confirmation, an instructional narrator and an interactive character can require different cadence even when the factual content is the same. Prepare the actual English words that should be spoken before synthesis.\n\nA request supports up to 30,000 characters. The producer’s approximate audio length beside this limit is not a fixed duration. For an interactive reply, keep one main thought and a clear ending; for a longer recording, divide related text at sentence or section boundaries. The shared TTS workflow documents neighbouring text or request context for preserving prosody across connected generations, so segmentation need not remove the relation between successive passages.\n\nFlash v2’s pause workflow uses SSML break tags. The product guide giveselevenlabs/eleven-flash-v2Eleven Flash v2 is ElevenLabs’ English-only text-to-speech model for responsive voice interactions. It converts prepared text into spoken audio, with a 30,000-character request limit and documented controls for pauses and individual-word pronunciation.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Eleven Flash v2 is ElevenLabs’ English-only speech-synthesis model for responsive voice applications. It takes a written utterance and produces spoken audio in the selected voice. The manufacturer positions Flash for real-time conversation and interactive experiences, such as assistant confirmations, spoken instructions and game responses. This named edition is separate from multilingual Flash v2.5 and the expressive v3 and v4 families.
English is the language profile of Flash v2. A voice can supply a regional accent and a particular tone, but it does not make this edition a multilingual model. Choose a voice that matches the intended listener and the purpose of the line. An assistant confirmation, an instructional narrator and an interactive character can require different cadence even when the factual content is the same. Prepare the actual English words that should be spoken before synthesis.
A request supports up to 30,000 characters. The producer’s approximate audio length beside this limit is not a fixed duration. For an interactive reply, keep one main thought and a clear ending; for a longer recording, divide related text at sentence or section boundaries. The shared TTS workflow documents neighbouring text or request context for preserving prosody across connected generations, so segmentation need not remove the relation between successive passages.
Flash v2’s pause workflow uses SSML break tags. The product guide gives <break time="1.5s" /> as a way to request a natural pause, with up to three seconds documented. The voice influences the delivery around the break, and excessive tags can cause speed changes, noise or artifacts. Use a break where the listener needs a transition, not between every word. Punctuation and ellipses can also influence timing but are less consistent and can add a hesitant tone.
Individual words can use SSML phoneme notation in IPA or CMU Arpabet. The manufacturer recommends CMU Arpabet for more predictable v2 pronunciation and says phoneme rules should be applied separately to each word of a multi-word name. Pronunciation dictionaries can retain the preferred phoneme or an alias for a recurring term; their matching is case-sensitive. This is different from v4’s native slash-wrapped IPA syntax and from the pronunciation profile of Flash v2.5.
Prepare reference codes, dates and abbreviations in the desired spoken form. The same digits can represent a quantity or an identifier, so specify whether the listener should hear a whole number or separate digits. Write the month and date unambiguously and expand abbreviations that should be spoken as words. Ordinary explanatory direction placed in the text may itself be read aloud; v3 and v4’s expressive audio tags are not the control profile described for this edition.
The producer’s format family includes MP3, uncompressed 16-bit PCM, μ-law and A-law for telephony, and Opus. The shared workflow can deliver a complete recording or return speech progressively. Voice settings influence stability, resemblance and pace, with a documented speed range of 0.7 to 1.2 and 1.0 unchanged. These settings guide a performance without guaranteeing an identical take or a precise final recording length.
For a practical English help message, give the result first, then one next step: confirm a saved selection, clearly pronounce the relevant field name and explain what the user can do next. For a tutorial, write a complete instruction and use a pause before the following action. Review the difficult names, numbers and transitions in the selected audio. Keep that take with its script and pronunciation preparation so it can become a reusable spoken cue, notification or assistant response.
POST /v1/audio/speechtextaudio| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits elevenlabs/eleven-flash-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 Flash 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-flash-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-flash-v2
Use the method paths shown above.